subject:(Person identification)

University of Houston

1. -4445-2186. An Interactive Pedestrian Re-Identification Tool with Semantic Based Re-Identification.

Degree: MS, Computer Science, 2016, University of Houston

► Person re-identification is an essential task of recognizing and matching people from non-overlapping cameras. A typical application of person re-identification is identifying a particular person… (more)

Subjects/Keywords: Person re-identification; Semantic

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

-4445-2186. (2016). An Interactive Pedestrian Re-Identification Tool with Semantic Based Re-Identification. (Masters Thesis). University of Houston. Retrieved from http://hdl.handle.net/10657/5431

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Chicago Manual of Style (16^th Edition):

-4445-2186. “An Interactive Pedestrian Re-Identification Tool with Semantic Based Re-Identification.” 2016. Masters Thesis, University of Houston. Accessed January 25, 2021. http://hdl.handle.net/10657/5431.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

MLA Handbook (7^th Edition):

-4445-2186. “An Interactive Pedestrian Re-Identification Tool with Semantic Based Re-Identification.” 2016. Web. 25 Jan 2021.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Vancouver:

-4445-2186. An Interactive Pedestrian Re-Identification Tool with Semantic Based Re-Identification. [Internet] [Masters thesis]. University of Houston; 2016. [cited 2021 Jan 25]. Available from: http://hdl.handle.net/10657/5431.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Council of Science Editors:

-4445-2186. An Interactive Pedestrian Re-Identification Tool with Semantic Based Re-Identification. [Masters Thesis]. University of Houston; 2016. Available from: http://hdl.handle.net/10657/5431

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

University of California – Irvine

2. Zhang, Liyan. Exploring Entity Resolution for Multimedia Person Identification.

Degree: Computer Science, 2014, University of California – Irvine

URL: http://www.escholarship.org/uc/item/9t59f756

► The explosion of massive media data induced by the proliferation of digital cameras, mobile devices as well as the emergence of online media websites, has… (more)

▼ The explosion of massive media data induced by the proliferation of digital cameras, mobile devices as well as the emergence of online media websites, has led us into the era of big data. Accurate and effective analyses of the big multimedia data to support semantically enriched representation in terms of events, activities, and entities can bring transformative improvements to a variety of application domains. The basic form of multimedia analysis for more sophisticated interpretation is characterized by questions such as ``who, what, where, when" that identify subjects, activities, locations, and time associated with images/video segments. In this thesis, we primarily focus on the ``who" question, which is referred as the person identification problem in multimedia data.While advances in image processing and computer vision has resulted in powerful techniques for person identification, such techniques based on the facial appearance representations, are usually prone to errors due to a variety of factors including noise, poor signal quality, occlusion, etc. It is widely recognized in the multimedia research community that additional contextual features can be leveraged to bring significant improvements to such tasks. Nevertheless, how to systematically utilize the heterogeneous contextual information still poses a big challenge. Besides, the person identification procedure is conventionally processed in an ``offline" setting where the typical goal is to achieve complete annotations of the whole collection before further applications. Such an ``offline " process is not tenable when dealing with big multimedia data, since the limitation of computational resources as well as restriction of manpower does not allow us to process every image with each possible tag and clean up every potentially noisy result.We note that similar challenges also arise in the database domain, especially for the entity resolution task. To address these challenges, recent entity resolution research has explored a series of powerful methods including techniques to exploit relationships, contextual information, domain semantics in the form of constraints and ontologies, etc. for the purpose of resolving references in structured/semi-structured and unstructured textual data. Additionally, query-driven data cleaning techniques have also been proposed and explored to resolve the challenges of big data.In this thesis, we aim to explore how such advanced entity resolution techniques can be exploited to improve semantic interpretation of multimedia data, specifically for the person identification problem. We first explore how to leverage the automatic data cleaning techniques to exploit relationships, contextual information, domain semantics, constraints, etc., to enhance the performance of face clustering and recognition. Then, we propose the new paradigm for face clustering/tagging suited for big data where image enrichment is seamlessly integrated into the image retrieval/analysis process – we refer to this new paradigm as ``query-driven image…

Subjects/Keywords: Computer science; Entity Resolution; Person Identification

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Zhang, L. (2014). Exploring Entity Resolution for Multimedia Person Identification. (Thesis). University of California – Irvine. Retrieved from http://www.escholarship.org/uc/item/9t59f756

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Zhang, Liyan. “Exploring Entity Resolution for Multimedia Person Identification.” 2014. Thesis, University of California – Irvine. Accessed January 25, 2021. http://www.escholarship.org/uc/item/9t59f756.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Zhang, Liyan. “Exploring Entity Resolution for Multimedia Person Identification.” 2014. Web. 25 Jan 2021.

Vancouver:

Zhang L. Exploring Entity Resolution for Multimedia Person Identification. [Internet] [Thesis]. University of California – Irvine; 2014. [cited 2021 Jan 25]. Available from: http://www.escholarship.org/uc/item/9t59f756.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Zhang L. Exploring Entity Resolution for Multimedia Person Identification. [Thesis]. University of California – Irvine; 2014. Available from: http://www.escholarship.org/uc/item/9t59f756

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Delft University of Technology

3. Yang, Hongyu (author). Improving Online Multi-Person Tracking Occlusion: Scale Loss for Deep ReID Feature Learning.

Degree: 2018, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:047f6900-3021-459c-9b4b-b5eda4a5c4a1

►

Occlusion and crossing in Multi-Person Tracking always influence the tracking results. In this paper, we show how deep Re-Identification (ReID), which aims at matching pedestrians… (more)

Subjects/Keywords: Multi-Person Tracking; Occlusion; Scale loss; Person Re-identification

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Yang, H. (. (2018). Improving Online Multi-Person Tracking Occlusion: Scale Loss for Deep ReID Feature Learning. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:047f6900-3021-459c-9b4b-b5eda4a5c4a1

Chicago Manual of Style (16^th Edition):

Yang, Hongyu (author). “Improving Online Multi-Person Tracking Occlusion: Scale Loss for Deep ReID Feature Learning.” 2018. Masters Thesis, Delft University of Technology. Accessed January 25, 2021. http://resolver.tudelft.nl/uuid:047f6900-3021-459c-9b4b-b5eda4a5c4a1.

MLA Handbook (7^th Edition):

Yang, Hongyu (author). “Improving Online Multi-Person Tracking Occlusion: Scale Loss for Deep ReID Feature Learning.” 2018. Web. 25 Jan 2021.

Vancouver:

Yang H(. Improving Online Multi-Person Tracking Occlusion: Scale Loss for Deep ReID Feature Learning. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Jan 25]. Available from: http://resolver.tudelft.nl/uuid:047f6900-3021-459c-9b4b-b5eda4a5c4a1.

Council of Science Editors:

Yang H(. Improving Online Multi-Person Tracking Occlusion: Scale Loss for Deep ReID Feature Learning. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:047f6900-3021-459c-9b4b-b5eda4a5c4a1

University of California – Riverside

4. Das, Abir. Active Learning in Multi-Camera Networks, With Applications in Person Re-Identification.

Degree: Electrical Engineering, 2015, University of California – Riverside

URL: http://www.escholarship.org/uc/item/46f0061k

► With the proliferation of cheap visual sensors, camera networks are everywhere. The ubiquitous presence of cameras opens the door for cutting edge research in processing… (more)

▼ With the proliferation of cheap visual sensors, camera networks are everywhere. The ubiquitous presence of cameras opens the door for cutting edge research in processing and analysis of the huge video data generated by such large-scale camera networks. Re-identification of persons coming in and out of the cameras is an important task. This has remained a challenge to the community for a variety of reasons such as change of scale, illumination, resolution etc. between cameras. All these leads to transformation of features between cameras which makes re-identification a challenging task. The first question that is addressed in this work is - Can we model the way features get transformed between cameras and use it to our advantage to re-identify persons between cameras with non-overlapping views? The similarity between the feature histograms and time series data motivated us to apply the principle of Dynamic Time Warping to study the transformation of features by warping the feature space. After capturing the feature warps, describing the transformation of features the variabilities of the warp functions were modeled as a function space of these feature warps. The function space not only allowed us to model feasible transformation between pairs of instances of the same target, but also to separate them from the infeasible transformations between instances of different targets. A supervised training phase is employed to learn a discriminating surface between these two classes in the function space.However, it is unlikely that supervised methods alone will be enough to deal with the volume and variety of data in such scenarios. The performance is dependent on tediously labeling the training data. Also supervised person re-identification strategies are static in the sense that these are unable to adapt to the changing dynamics of continuous streaming data. Active participation of human expert is necessary in such scenario. The human labor is reduced if the human is involved for the most difficult cases and if it can be made sure that the human expert is not asked to do the same job repetitively. So the question we addressed is the following. Is it possible to identify a manageable set of informative, but non-redundant, samples for labeling by a human expert? Moreover, is it possible to select these examples progressively in an online setting where all the training data may not be available a priori? The second work explored a convex optimization based iterative framework that progressively and judiciously chooses a sparse but informative set of samples for labeling, with minimal overlap with previously labeled images. The third work also addresses the same basic question from a different perspective where the human effort is reduced in two ways - by changing the questions asked to the human annotator to binary yes-no type instead of multiple choice and by incorporating the domain knowledge from the human how a human expert discriminates between persons. The two objectives are fulfilled by employing a ‘value of information’…

Subjects/Keywords: Electrical engineering; Active Learning; Feature Transformation; Person Re-identification

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Das, A. (2015). Active Learning in Multi-Camera Networks, With Applications in Person Re-Identification. (Thesis). University of California – Riverside. Retrieved from http://www.escholarship.org/uc/item/46f0061k

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Das, Abir. “Active Learning in Multi-Camera Networks, With Applications in Person Re-Identification.” 2015. Thesis, University of California – Riverside. Accessed January 25, 2021. http://www.escholarship.org/uc/item/46f0061k.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Das, Abir. “Active Learning in Multi-Camera Networks, With Applications in Person Re-Identification.” 2015. Web. 25 Jan 2021.

Vancouver:

Das A. Active Learning in Multi-Camera Networks, With Applications in Person Re-Identification. [Internet] [Thesis]. University of California – Riverside; 2015. [cited 2021 Jan 25]. Available from: http://www.escholarship.org/uc/item/46f0061k.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Das A. Active Learning in Multi-Camera Networks, With Applications in Person Re-Identification. [Thesis]. University of California – Riverside; 2015. Available from: http://www.escholarship.org/uc/item/46f0061k

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

5. Miryala, Chandra Mohan. Novel methods on Facial images for age classification and person identification;.

Degree: 2010, Jawaharlal Nehru Technological University

URL: http://shodhganga.inflibnet.ac.in/handle/10603/2417

►

As one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention, especially in the recent past. There… (more)

▼

As one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention, especially in the recent past. There are at least two reasons for this trend; first is the wide range of commercial and law enforcement applications such as smart cards, access control, passports, credit cards, driving licenses, biometric authentication, video surveillance, and information security, among others and the second is the availability of feasible technologies after 30 years of research. The thesis mainly concentrated on textural properties of skin for face recognition and age classification. Initially facial properties are derived by exploring statistical texture features (STF) of co-occurrence matrices. A precise Face recognition is carried out on STF by a new distance function scheme that eliminates retrieved facial images based on significant texture features. One of the major drawback of most of the Face Recognition Methods are, they fail in recognizing the humans, if there is a variation in terms of age between probe and database facial image, because there will be significant changes in the face when a person acquires age. For this, a new direction for the child and adult classification using texture features derived from geometric properties of human face is proposed. The texture features of the present approach are computed from facial distance features. newlineThe advantage of the proposed approach is, it can be effectively used for persons with folded eye, blind, wearing spectacles, and face images with closed eyes. Generally the bone structural changes do not occur after the person is fully grown that is the geometric relationships of primary features do not vary. To extend the age classification problem further, secondary features based on Topological Texture Features in the facial skin are identified and exploited in the present study.

Abstract includes, References p.137-155

Advisors/Committee Members: Vakulabharanam, Vijaya Kumar.

Subjects/Keywords: Person Identification; Wavelets; Facial Skin; Face Recognition; Human Face

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Miryala, C. M. (2010). Novel methods on Facial images for age classification and person identification;. (Thesis). Jawaharlal Nehru Technological University. Retrieved from http://shodhganga.inflibnet.ac.in/handle/10603/2417

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Miryala, Chandra Mohan. “Novel methods on Facial images for age classification and person identification;.” 2010. Thesis, Jawaharlal Nehru Technological University. Accessed January 25, 2021. http://shodhganga.inflibnet.ac.in/handle/10603/2417.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Miryala, Chandra Mohan. “Novel methods on Facial images for age classification and person identification;.” 2010. Web. 25 Jan 2021.

Vancouver:

Miryala CM. Novel methods on Facial images for age classification and person identification;. [Internet] [Thesis]. Jawaharlal Nehru Technological University; 2010. [cited 2021 Jan 25]. Available from: http://shodhganga.inflibnet.ac.in/handle/10603/2417.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Miryala CM. Novel methods on Facial images for age classification and person identification;. [Thesis]. Jawaharlal Nehru Technological University; 2010. Available from: http://shodhganga.inflibnet.ac.in/handle/10603/2417

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Mykolas Romeris University

6. Trakšelytė, Agnė. Viešosios elektroninės paslaugos: asmens identifikavimo problemos.

Degree: Master, Marketing and Administration, 2008, Mykolas Romeris University

URL: http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2008~D_20080207_110240-72653 ;

►

Informacinių technologijų pasiekimų pritaikymas valstybės valdymui atveria naujas didžiules galimybes gyventojų bendradarbiavimui su valdžios institucijomis, skaidresniam valdymui, aiškesniam sprendimų priėmimui. Jis sudaro gyventojui visiškai naujas… (more)

▼

Informacinių technologijų pasiekimų pritaikymas valstybės valdymui atveria naujas didžiules galimybes gyventojų bendradarbiavimui su valdžios institucijomis, skaidresniam valdymui, aiškesniam sprendimų priėmimui. Jis sudaro gyventojui visiškai naujas galimybes bendrauti ir dirbti su viešojo administravimo institucijomis sau patogiu laiku, bet kurioje vietoje ir įvairiais būdais. Kai paslaugos pradėtos perkelti į elektroninę erdvę, iškilo svarbus klausimas: kaip atpažinti asmenį prieš suteikiant jam informaciją? Prieš pateikiant duomenis informacijos tiekėjas turi įsitikinti, kad perduoda duomenis būtent tam asmeniui, kuris padarė užklausą. Atitinkamai užklausą padaręs asmuo turi autentifikuoti save, arba kitaip sakant įrodyti savo tapatybę. E-valdžios koncepcijoje taip pat buvo planuota sukurti asmens identifikavimo sistemą, atitinkančią Europos Sąjungos reikalavimus. Ji turėtų neklystamai identifikuoti asmenį ir informacinių technologijų pagalba bendrauti su viešojo administravimo institucijomis. Darbo tikslas – įvertinti galimus ir perspektyvius asmens identifikavimo būdus; išanalizuoti jų patikimumo, saugumo ir sąveikumo aspektus; pateikti numatomų priemonių rekomendacijas. Uždaviniai: 1. išnagrinėti esamus bei alternatyvius asmens identifikavimo elektroninėje erdvėje būdus; 2. apžvelgti naujausių technologijų siūlomus asmens identifikavimo būdus; 3. išanalizuoti geriausius asmens identifikavimo pavyzdžius Europos Sąjungoje bei kitose užsienio šalyse; 4. atlikus tyrimą... [toliau žr. visą tekstą]

Adaptation of information technologies to the country’s administration opens up new opportunities for residents’ cooperation with the governmental institutions, for more transparent administration and clearer decision-making process. It also presents new possibilities for a citizen to communicate and work with public administration institutions on convenient time, place and ways. When some services were moved to electronic space, an important question was raised: how to recognise people before any information was presented to them? Information supplier has to make sure he was transferring requested information to the person who had placed the request. Also, the person, who placed the request, has to identify himself or to prove his identity. The identification system meeting the requirements of the European Union was also planned to be created while drafting the concept of e-government. This system should infallibly identify a person and communicate with public administration institution with the help of information technologies. The aim of the paper – is to evaluate possible and promising person identification ways; to analyse the aspects of their reliability, safety and interaction; and to supply recommendations of anticipatory measures. Objectives: 1. to discuss current and alternative ways to identify a person in electronic space; 2. to review identification solutions presented by the newest information technologies; 3. to analyse the best examples of person... [to full text]

Advisors/Committee Members: Petrauskas, Rimantas Alfonsas (Master’s thesis supervisor), Keras, Antanas (Master’s thesis reviewer), Augustinaitis, Arūnas (Master’s degree committee member), Dzemydienė, Dalė (Master’s degree committee member), Kmeliauskaitė, Jolanta (Master’s degree session secretary), Rudzkienė, Vitalija (Master’s degree committee chair), Petrauskas, Rimantas Alfonsas (Master’s degree committee member).

Subjects/Keywords: Asmens identifikavimas; Elektroninė valdžia; E.paslaugos; Person identification; E-government; E-services

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Trakšelytė, Agnė. (2008). Viešosios elektroninės paslaugos: asmens identifikavimo problemos. (Masters Thesis). Mykolas Romeris University. Retrieved from http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2008~D_20080207_110240-72653 ;

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Chicago Manual of Style (16^th Edition):

Trakšelytė, Agnė. “Viešosios elektroninės paslaugos: asmens identifikavimo problemos.” 2008. Masters Thesis, Mykolas Romeris University. Accessed January 25, 2021. http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2008~D_20080207_110240-72653 ;.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

MLA Handbook (7^th Edition):

Trakšelytė, Agnė. “Viešosios elektroninės paslaugos: asmens identifikavimo problemos.” 2008. Web. 25 Jan 2021.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Vancouver:

Trakšelytė, Agnė. Viešosios elektroninės paslaugos: asmens identifikavimo problemos. [Internet] [Masters thesis]. Mykolas Romeris University; 2008. [cited 2021 Jan 25]. Available from: http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2008~D_20080207_110240-72653 ;.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Council of Science Editors:

Trakšelytė, Agnė. Viešosios elektroninės paslaugos: asmens identifikavimo problemos. [Masters Thesis]. Mykolas Romeris University; 2008. Available from: http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2008~D_20080207_110240-72653 ;

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

University of California – Riverside

7. Panda, Rameswar. Visual Learning with Weak Supervision: Applications in Video Summarization and Person Re-Identification.

Degree: Electrical Engineering, 2018, University of California – Riverside

URL: http://www.escholarship.org/uc/item/7w08k4sd

► Many of the recent successes in computer vision have been driven by the availability of large quantities of labeled training data. However, in the vast… (more)

▼ Many of the recent successes in computer vision have been driven by the availability of large quantities of labeled training data. However, in the vast majority of real-world settings, collecting such data sets by hand is infeasible due to the cost of labeling data or the paucity of data in a given domain. One increasingly popular approach is to use weaker forms of supervision that are potentially less precise but can be substantially less costly than producing explicit annotation for the given task. Examples include domain knowledge, weakly labeled data from the web, constraints due to physics of the problem or intuition, noisy labels from distant supervision, unreliable annotations obtained from the crowd workers, and transfer learning settings. In this thesis, we explore two important and highly challenging problems in computer vision, namely video summarization and person re-identification, where learning with weak supervision could be extremely useful but remains as a largely under-addressed problem in the literature.One common assumption of many existing video summarization methods is that videos are independent of each other, and hence the summarization tasks are conducted separately by neglecting relationships that possibly reside across the videos. In the first approach, we investigate how topic-related videos can provide more knowledge and useful clues to extract summary from a given video. We develop a sparse optimization framework for finding a set of representative and diverse shots that simultaneously capture both important particularities arising in the given video, as well as, generalities identified from the set of topic-related videos. In the second approach, we present a novel multi-view video summarization framework by exploiting the data correlations through an embedding without assuming any prior correspondences/alignment between the multi-view videos, e.g., uncalibrated camera networks. Via extensive experimentation on different benchmark datasets, we validate both of our approaches and demonstrate that our frameworks are able to extract better quality video summaries compared to the state-of-the-art alternatives.Most work in person re-identification has focused on a fixed network of cameras. However, in practice, new camera(s) may be added, either permanently or on a temporary basis. In the final part of the dissertation, we show that it is possible to on-board new camera(s) to an existing network using domain adaptation techniques with limited additional supervision. We develop a domain perceptive re-identification framework that can effectively discover and transfer knowledge from the best source camera (already installed) to a newly introduced target camera(s), without requiring a very expensive training phase. Our approach can greatly increase the flexibility and reduce the deployment cost of new cameras in many real-world dynamic camera networks.

Subjects/Keywords: Electrical engineering; Computer science; Person Re-identification; Video Summarization

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Panda, R. (2018). Visual Learning with Weak Supervision: Applications in Video Summarization and Person Re-Identification. (Thesis). University of California – Riverside. Retrieved from http://www.escholarship.org/uc/item/7w08k4sd

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Panda, Rameswar. “Visual Learning with Weak Supervision: Applications in Video Summarization and Person Re-Identification.” 2018. Thesis, University of California – Riverside. Accessed January 25, 2021. http://www.escholarship.org/uc/item/7w08k4sd.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Panda, Rameswar. “Visual Learning with Weak Supervision: Applications in Video Summarization and Person Re-Identification.” 2018. Web. 25 Jan 2021.

Vancouver:

Panda R. Visual Learning with Weak Supervision: Applications in Video Summarization and Person Re-Identification. [Internet] [Thesis]. University of California – Riverside; 2018. [cited 2021 Jan 25]. Available from: http://www.escholarship.org/uc/item/7w08k4sd.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Panda R. Visual Learning with Weak Supervision: Applications in Video Summarization and Person Re-Identification. [Thesis]. University of California – Riverside; 2018. Available from: http://www.escholarship.org/uc/item/7w08k4sd

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Houston

8. Wei, Li 1988-. Contextual Information for Applications in Video Surveillance.

Degree: PhD, Computer Science, 2016, University of Houston

URL: http://hdl.handle.net/10657/5394

► With a growing network of cameras being used for security applications, video-based monitoring relying on human operators is ineffective and lacking in reliability and scalability.… (more)

▼ With a growing network of cameras being used for security applications, video-based monitoring relying on human operators is ineffective and lacking in reliability and scalability. In this thesis, I present automatic solutions that enable monitoring of humans in videos, such as identifying same individuals across different cameras (human re-identification) and recognizing human activities. Analyzing videos using only individual-based features can be very challenging because of the significant appearance and motion variance due to the changing viewpoints, different lighting conditions, and occlusions. Motivated by the fact that people often form groups, it is feasible to model the interaction among group members to disambiguate the individual features in video analysis tasks. This thesis introduces features that leverage the human group as contextual information and demonstrates its performance for the tasks of human re-identification and activity recognition. Two descriptors are introduced for human re-identification. The Subject Centric Group (SCG) feature captures a person’s group appearance and shape information using the estimate of persons' positions in 3D space. The metric is designed to consider both human appearance and group similarity. The Spatial Appearance Group (SAG) feature extracts group appearance and shape information directly from video frames. A random-forest model is trained to predict the group's similarity score. For human activity recognition, I propose context features along with a deep model to recognize the individual subject’s activity in videos of real-world scenes. Besides the motion features of the person, I also utilize group context information and scene context information to improve the recognition performance. This thesis demonstrates the application of proposed features in both problems. Our experiments show that proposed features can reach state-of-the-art accuracy on challenging re-identification datasets that represent real-world scenario, and can also outperform state-of-the art human activity recognition methods on 5-activities and 6-activities versions of the Collective Activities dataset. Advisors/Committee Members: Shah, Shishir Kirit (advisor), Subhlok, Jaspal (committee member), Gabriel, Edgar (committee member), Prasad, Saurabh (committee member).

Subjects/Keywords: Context Information; Person re-identification; Activity recognition; Video analytics

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Wei, L. 1. (2016). Contextual Information for Applications in Video Surveillance. (Doctoral Dissertation). University of Houston. Retrieved from http://hdl.handle.net/10657/5394

Chicago Manual of Style (16^th Edition):

Wei, Li 1988-. “Contextual Information for Applications in Video Surveillance.” 2016. Doctoral Dissertation, University of Houston. Accessed January 25, 2021. http://hdl.handle.net/10657/5394.

MLA Handbook (7^th Edition):

Wei, Li 1988-. “Contextual Information for Applications in Video Surveillance.” 2016. Web. 25 Jan 2021.

Vancouver:

Wei L1. Contextual Information for Applications in Video Surveillance. [Internet] [Doctoral dissertation]. University of Houston; 2016. [cited 2021 Jan 25]. Available from: http://hdl.handle.net/10657/5394.

Council of Science Editors:

Wei L1. Contextual Information for Applications in Video Surveillance. [Doctoral Dissertation]. University of Houston; 2016. Available from: http://hdl.handle.net/10657/5394

University of Cambridge

9. Pfeil, Katrin. The Effectiveness of the Self-Administered Interview© - A Meta-Analytic Review and Empirical Study with Older Adult Witnesses.

Degree: PhD, 2018, University of Cambridge

URL: https://www.repository.cam.ac.uk/handle/1810/274905

► The Self-Administered Interview© (SAI©) is an eyewitness interviewing tool designed to help protect eyewitness memory and elicit a comprehensive initial statement (Gabbert, Hope, & Fisher,… (more)

▼ The Self-Administered Interview© (SAI©) is an eyewitness interviewing tool designed to help protect eyewitness memory and elicit a comprehensive initial statement (Gabbert, Hope, & Fisher, 2009). Early research shows promising results in general adult samples. Whether the SAI© is an effective tool for older adult witnesses has not yet been fully addressed. Older adults will become increasingly important as a witness population in the future, yet perform worse compared to young adults. Some attempts have been made to aid older adult witnesses, but an easy-to-apply and effective method is yet to be introduced. This dissertation presents an overview of current knowledge on eyewitnesses and provides a theoretical basis for the empirical chapters. It further presents results of a systematic review and several meta-analyses on the effectiveness of the SAI© as a means to enhance eyewitness testimony. The meta-analyses cover 38 experimental comparisons from 22 empirical studies representing 1712 interviewees. Results indicate a strong benefit of the SAI both immediately after the witnessed crime (d = 1.20) and in a delayed recall (d = 0.92 compared to no initial recall) after one to three weeks. The third large chapter of this dissertation presents the results of an experiment that investigated the effectiveness of the SAI© for older witnesses’ testimony, suggestibility and lineup performance. 144 participants, half of which were 60 years or older and half aged 18-30 years, took part in two sessions. In the first session, they were shown a film of a staged crime and either filled in the SAI©, gave a written free recall or no initial recall. In the second session after one week they were then asked to give a free recall of what they remembered, answer questions including suggestive questions, and also to identify the perpetrator from the film from a 6-person simultaneous photo lineup. Results confirm the classic SAI© effect for young adults, show a small beneficial effect for older adults and also indicate a beneficial effect for lineup performance for the first time.

Subjects/Keywords: Eyewitnesses; Investigative Interviewing; Meta-Analysis; Self-Administered Interview; Testimony; Person Identification

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Pfeil, K. (2018). The Effectiveness of the Self-Administered Interview© - A Meta-Analytic Review and Empirical Study with Older Adult Witnesses. (Doctoral Dissertation). University of Cambridge. Retrieved from https://www.repository.cam.ac.uk/handle/1810/274905

Chicago Manual of Style (16^th Edition):

Pfeil, Katrin. “The Effectiveness of the Self-Administered Interview© - A Meta-Analytic Review and Empirical Study with Older Adult Witnesses.” 2018. Doctoral Dissertation, University of Cambridge. Accessed January 25, 2021. https://www.repository.cam.ac.uk/handle/1810/274905.

MLA Handbook (7^th Edition):

Pfeil, Katrin. “The Effectiveness of the Self-Administered Interview© - A Meta-Analytic Review and Empirical Study with Older Adult Witnesses.” 2018. Web. 25 Jan 2021.

Vancouver:

Pfeil K. The Effectiveness of the Self-Administered Interview© - A Meta-Analytic Review and Empirical Study with Older Adult Witnesses. [Internet] [Doctoral dissertation]. University of Cambridge; 2018. [cited 2021 Jan 25]. Available from: https://www.repository.cam.ac.uk/handle/1810/274905.

Council of Science Editors:

Pfeil K. The Effectiveness of the Self-Administered Interview© - A Meta-Analytic Review and Empirical Study with Older Adult Witnesses. [Doctoral Dissertation]. University of Cambridge; 2018. Available from: https://www.repository.cam.ac.uk/handle/1810/274905

Delft University of Technology

10. Priadi Teguh Wibowo, Priadi (author). Automatic Running Event Visualization using Video from Multiple Camera.

Degree: 2019, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:9b246dbe-2708-4aa4-808b-36b92b040174

►

Visualizing runners trajectory from video data is not straightforward because the video data does not contain the explicit information of which runners appear in the… (more)

Subjects/Keywords: Computer Vision; Deep Learning; Visualization; Person Re-identification; Scene Text Recognition

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Priadi Teguh Wibowo, P. (. (2019). Automatic Running Event Visualization using Video from Multiple Camera. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:9b246dbe-2708-4aa4-808b-36b92b040174

Chicago Manual of Style (16^th Edition):

Priadi Teguh Wibowo, Priadi (author). “Automatic Running Event Visualization using Video from Multiple Camera.” 2019. Masters Thesis, Delft University of Technology. Accessed January 25, 2021. http://resolver.tudelft.nl/uuid:9b246dbe-2708-4aa4-808b-36b92b040174.

MLA Handbook (7^th Edition):

Priadi Teguh Wibowo, Priadi (author). “Automatic Running Event Visualization using Video from Multiple Camera.” 2019. Web. 25 Jan 2021.

Vancouver:

Priadi Teguh Wibowo P(. Automatic Running Event Visualization using Video from Multiple Camera. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Jan 25]. Available from: http://resolver.tudelft.nl/uuid:9b246dbe-2708-4aa4-808b-36b92b040174.

Council of Science Editors:

Priadi Teguh Wibowo P(. Automatic Running Event Visualization using Video from Multiple Camera. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:9b246dbe-2708-4aa4-808b-36b92b040174

Tampere University

11. Yrjänäinen, Jukka. Privacy conscious computer vision .

Degree: 2020, Tampere University

URL: https://trepo.tuni.fi/handle/10024/121922

► This work describes the design and the implementation of the distributed computer vision solution for person tracking and counting in a public museum. The system… (more)

▼ This work describes the design and the implementation of the distributed computer vision solution for person tracking and counting in a public museum. The system consists of an edge device fleet that does send data to a cloud server for further analysis. The key design goal is the protection of the privacy of the persons being monitored. This is achieved by a system that does not send actual images to the server, instead detected persons are represented with a feature vector extracted from the images. Privacy sensitive image data is not stored or transmitted anywhere in the system. Device design consists of Raspberry Pi single-board computers equipped with a neural network acceleration hardware and a camera module. These devices are used to locate a person from the camera view with the object detection neural network. After object detection a re-identification neural network is applied to the found object to generate a feature vector representation. This vector is sent to the cloud server. Based on the feature vectors it is possible to associate detected people across multiple cameras and moments time. However, it is not possible to reconstruct the original image from the feature vector. The experiments and performance measurements with edge devices show that the simultaneous use of deep neural networks for object detection and feature generation using relatively low-cost hardware is feasible. The design recommendation based on the experiments is that the use of a dedicated HW accelerator for running all neural networks is preferred. The analysis also show that the variation of the accuracy and computational complexity of used neural networks offers a range of feasible performance trade-offs. The data analysis method in the server using only feature vector data for tracking and clustering is evaluated. The experiments with publicly available image dataset indicate that with the proposed approach it is possible to approximate person count with reasonable accuracy.

Subjects/Keywords: computer vision ; neural networks ; object detection ; person re-identification ; edge computing

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Yrjänäinen, J. (2020). Privacy conscious computer vision . (Masters Thesis). Tampere University. Retrieved from https://trepo.tuni.fi/handle/10024/121922

Chicago Manual of Style (16^th Edition):

Yrjänäinen, Jukka. “Privacy conscious computer vision .” 2020. Masters Thesis, Tampere University. Accessed January 25, 2021. https://trepo.tuni.fi/handle/10024/121922.

MLA Handbook (7^th Edition):

Yrjänäinen, Jukka. “Privacy conscious computer vision .” 2020. Web. 25 Jan 2021.

Vancouver:

Yrjänäinen J. Privacy conscious computer vision . [Internet] [Masters thesis]. Tampere University; 2020. [cited 2021 Jan 25]. Available from: https://trepo.tuni.fi/handle/10024/121922.

Council of Science Editors:

Yrjänäinen J. Privacy conscious computer vision . [Masters Thesis]. Tampere University; 2020. Available from: https://trepo.tuni.fi/handle/10024/121922

Universitat Politècnica de València

12. Oliver Moll, Javier. PERSON RE-IDENTIFICATION USING RGB-DEPTH CAMERAS .

Degree: 2015, Universitat Politècnica de València

URL: http://hdl.handle.net/10251/59227

► [EN] The presence of surveillance systems in our lives has drastically increased during the last years. Camera networks can be seen in almost every crowded… (more)

▼ [EN] The presence of surveillance systems in our lives has drastically increased during the last years. Camera networks can be seen in almost every crowded public and private place, which generate huge amount of data with valuable information. The automatic analysis of data plays an important role to extract relevant information from the scene. In particular, the problem of person re-identification is a prominent topic that has become of great interest, specially for the fields of security or marketing. However, there are some factors, such as changes in the illumination conditions, variations in the person pose, occlusions or the presence of outliers that make this topic really challenging. Fortunately, the recent introduction of new technologies such as depth cameras opens new paradigms in the image processing field and brings new possibilities. This Thesis proposes a new complete framework to tackle the problem of person re-identification using commercial rgb-depth cameras. This work includes the analysis and evaluation of new approaches for the modules of segmentation, tracking, description and matching. To evaluate our contributions, a public dataset for person re-identification using rgb-depth cameras has been created. Rgb-depth cameras provide accurate 3D point clouds with color information. Based on the analysis of the depth information, an novel algorithm for person segmentation is proposed and evaluated. This method accurately segments any person in the scene, and naturally copes with occlusions and connected people. The segmentation mask of a person generates a 3D person cloud, which can be easily tracked over time based on proximity. The accumulation of all the person point clouds over time generates a set of high dimensional color features, named raw features, that provides useful information about the person appearance. In this Thesis, we propose a family of methods to extract relevant information from the raw features in different ways. The first approach compacts the raw features into a single color vector, named Bodyprint, that provides a good generalisation of the person appearance over time. Second, we introduce the concept of 3D Bodyprint, which is an extension of the Bodyprint descriptor that includes the angular distribution of the color features. Third, we characterise the person appearance as a bag of color features that are independently generated over time. This descriptor receives the name of Bag of Appearances because its similarity with the concept of Bag of Words. Finally, we use different probabilistic latent variable models to reduce the feature vectors from a statistical perspective. The evaluation of the methods demonstrates that our proposals outperform the state of the art.; [ES] La presencia de sistemas de vigilancia se ha incrementado notablemente en los últimos anños. Las redes de videovigilancia pueden verse en casi cualquier espacio público y privado concurrido, lo cual genera una gran cantidad de datos de gran valor. El análisis automático de la información juega un papel… Advisors/Committee Members: Albiol Colomer, Alberto (advisor).

Subjects/Keywords: Computer vision; Artificial vision; Person re-identification; Person detection; Person description; Tracking; Matching; Kinect; Bodyprint; 3d bodyprint; Bag of appearances; Latent features

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Oliver Moll, J. (2015). PERSON RE-IDENTIFICATION USING RGB-DEPTH CAMERAS . (Doctoral Dissertation). Universitat Politècnica de València. Retrieved from http://hdl.handle.net/10251/59227

Chicago Manual of Style (16^th Edition):

Oliver Moll, Javier. “PERSON RE-IDENTIFICATION USING RGB-DEPTH CAMERAS .” 2015. Doctoral Dissertation, Universitat Politècnica de València. Accessed January 25, 2021. http://hdl.handle.net/10251/59227.

MLA Handbook (7^th Edition):

Oliver Moll, Javier. “PERSON RE-IDENTIFICATION USING RGB-DEPTH CAMERAS .” 2015. Web. 25 Jan 2021.

Vancouver:

Oliver Moll J. PERSON RE-IDENTIFICATION USING RGB-DEPTH CAMERAS . [Internet] [Doctoral dissertation]. Universitat Politècnica de València; 2015. [cited 2021 Jan 25]. Available from: http://hdl.handle.net/10251/59227.

Council of Science Editors:

Oliver Moll J. PERSON RE-IDENTIFICATION USING RGB-DEPTH CAMERAS . [Doctoral Dissertation]. Universitat Politècnica de València; 2015. Available from: http://hdl.handle.net/10251/59227

13. Chen, Yiqiang. Person re-identification in images with deep learning : Ré-identification de personnes dans des images par apprentissage automatique.

Degree: Docteur es, Informatique, 2018, Lyon

URL: http://www.theses.fr/2018LYSEI074

►

La vidéosurveillance est d’une grande valeur pour la sécurité publique. En tant que l’un des plus importantes applications de vidéosurveillance, la ré-identification de personnes est… (more)

▼

La vidéosurveillance est d’une grande valeur pour la sécurité publique. En tant que l’un des plus importantes applications de vidéosurveillance, la ré-identification de personnes est définie comme le problème de l’identification d’individus dans des images captées par différentes caméras de surveillance à champs non-recouvrants. Cependant, cette tâche est difficile à cause d’une série de défis liés à l’apparence de la personne, tels que les variations de poses, de point de vue et de l’éclairage etc. Pour régler ces différents problèmes, dans cette thèse, nous proposons plusieurs approches basées sur l’apprentissage profond de sorte d’améliorer de différentes manières la performance de ré-identification. Dans la première approche, nous utilisons les attributs des piétons tels que genre, accessoires et vêtements. Nous proposons un système basé sur un réseau de neurones à convolution(CNN) qui est composé de deux branches : une pour la classification d’identité et l’autre pour la reconnaissance d’attributs. Nous fusionnons ensuite ces deux branches pour la ré-identification. Deuxièmement, nous proposons un CNN prenant en compte différentes orientations du corps humain. Le système fait une estimation de l’orientation et, de plus, combine les caractéristiques de différentes orientations extraites pour être plus robuste au changement de point de vue. Comme troisième contribution de cette thèse, nous proposons une nouvelle fonction de coût basée sur une liste d’exemples. Elle introduit une pondération basée sur le désordre du classement et permet d’optimiser directement les mesures d’évaluation. Enfin, pour un groupe de personnes, nous proposons d’extraire une représentation de caractéristiques visuelles invariante à la position d’un individu dans une image de group. Cette prise en compte de contexte de groupe réduit ainsi l’ambigüité de ré-identification. Pour chacune de ces quatre contributions, nous avons effectué de nombreuses expériences sur les différentes bases de données publiques pour montrer l’efficacité des approches proposées.

Video surveillance systems are of a great value for public safety. As one of the most import surveillance applications, person re-identification is defined as the problem of identifying people across images that have been captured by different surveillance cameras without overlapping fields of view. With the increasing need for automated video analysis, this task is increasingly receiving attention. However, this problem is challenging due to the large variations of lighting, pose, viewpoint and background. To tackle these different difficulties, in this thesis, we propose several deep learning based approaches to obtain a better person re-identification performance in different ways. In the first proposed approach, we use pedestrian attributes to enhance the person re-identification. The attributes are defined as semantic mid-level descriptions of persons, such as gender, accessories, clothing etc. They could be helpful to extract characteristics that are invariant to the pose and…

Advisors/Committee Members: Baskurt, Atilla (thesis director).

Subjects/Keywords: Informatique; Vision par ordinateur; Apprentissage automatique; Ré-Identification de personne; Information Technology; Computer vision; Deep Learning; Person re-Identification; 006.407 2

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Chen, Y. (2018). Person re-identification in images with deep learning : Ré-identification de personnes dans des images par apprentissage automatique. (Doctoral Dissertation). Lyon. Retrieved from http://www.theses.fr/2018LYSEI074

Chicago Manual of Style (16^th Edition):

Chen, Yiqiang. “Person re-identification in images with deep learning : Ré-identification de personnes dans des images par apprentissage automatique.” 2018. Doctoral Dissertation, Lyon. Accessed January 25, 2021. http://www.theses.fr/2018LYSEI074.

MLA Handbook (7^th Edition):

Chen, Yiqiang. “Person re-identification in images with deep learning : Ré-identification de personnes dans des images par apprentissage automatique.” 2018. Web. 25 Jan 2021.

Vancouver:

Chen Y. Person re-identification in images with deep learning : Ré-identification de personnes dans des images par apprentissage automatique. [Internet] [Doctoral dissertation]. Lyon; 2018. [cited 2021 Jan 25]. Available from: http://www.theses.fr/2018LYSEI074.

Council of Science Editors:

Chen Y. Person re-identification in images with deep learning : Ré-identification de personnes dans des images par apprentissage automatique. [Doctoral Dissertation]. Lyon; 2018. Available from: http://www.theses.fr/2018LYSEI074

14. Gay, Paul. Segmentation et identification audiovisuelle de personnes dans des journaux télévisés : Audiovisual segmentation and identification of persons in broadcast news.

Degree: Docteur es, Informatique, 2015, Le Mans

URL: http://www.theses.fr/2015LEMA1021

►

Cette thèse traite de l’identification des locuteurs et des visages dans les journaux télévisés. L’identification est effectuée à partir des noms affichés à l’écran dans… (more)

▼

Cette thèse traite de l’identification des locuteurs et des visages dans les journaux télévisés. L’identification est effectuée à partir des noms affichés à l’écran dans les cartouches qui servent couramment à annoncer les locuteurs. Puisque ces cartouches apparaissent parcimonieusement dans la vidéo, obtenir de bonnes performances d’identification demande une bonne qualité du regroupement audiovisuel des personnes. Par regroupement, on entend ici la tâche de détecteret regrouper tous les instants où une personne parle ou apparaît. Cependant les variabilités intra-personnes gênent ce regroupement. Dans la modalité audio, ces variabilités sont causées par la parole superposée et les bruits de fond. Dans la modalité vidéo, elles correspondent essentiellement à des variations de la pose des visages dans les scènes de plateaux avec, en plus, des variations de luminosité (notamment dans le cas des reportages). Dans cette thèse, nous proposons une modélisation du contexte de la vidéo est proposée afin d’optimiser le regroupement pour une meilleure identification. Dans un premier temps, un modèle basé sur les CRF est proposé afin d’effectuer le regroupement audiovisuel des personnes de manière jointe. Dans un second temps, un système d’identification est mis en place, basé sur la combinaison d’un CRF de nommage à l’échelle des classes, et du CRF développé précédemment pour le regroupement. En particulier, des informations de contexte extraites de l’arrière plan des images et des noms extraits des cartouches sont intégrées dans le CRF de regroupement. Ces éléments permettent d’améliorer le regroupement et d’obtenir des gains significatifs en identification dans les scènes de plateaux.

This Phd thesis is about speaker and face identification in broadcast news. The identification is relying on the names automatically extracted from overlaid texts which are used to announce the speakers. Since those names appear sparsely in the video, identification performance depends on the diarization performance i.e. the capacity of detecting and clustering together all the moments when a given person appears or speaks. However, intra-person variability in the video signal make this task difficult. In the audio modality, this variability comes from overlap speech and background noise. For the video, it consists in head pose variations and lighting conditions (especially in report scenes). A context-aware model is proposed to optimize the diarization for a better identification. Firstly, a Conditional Random Field (CRF) model isproposed to perform the diarization jointly over the speech segments and the face tracks. Secondly, an identifcation system is designed. It is based on the combination of a naming CRF at cluster level and the diarization CRF. In particular, context information extracted from the image background and the names extracted from the overlaid texts are integrated in the diarization CRF at segment level. The use of those elements enable us to obtain better performances in diarization and identification, especially in…

Advisors/Committee Members: Deléglise, Paul (thesis director), Odobez, Jean-Marc (thesis director), Meignier, Sylvain (thesis director).

Subjects/Keywords: Regroupement audiovisuel; Journaux télévisés; Champ conditionnel aléatoire; Identification de personnes; Audiovisual diarization; Broadcast news; Conditional random field; Person identification; 006.4

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Gay, P. (2015). Segmentation et identification audiovisuelle de personnes dans des journaux télévisés : Audiovisual segmentation and identification of persons in broadcast news. (Doctoral Dissertation). Le Mans. Retrieved from http://www.theses.fr/2015LEMA1021

Chicago Manual of Style (16^th Edition):

Gay, Paul. “Segmentation et identification audiovisuelle de personnes dans des journaux télévisés : Audiovisual segmentation and identification of persons in broadcast news.” 2015. Doctoral Dissertation, Le Mans. Accessed January 25, 2021. http://www.theses.fr/2015LEMA1021.

MLA Handbook (7^th Edition):

Gay, Paul. “Segmentation et identification audiovisuelle de personnes dans des journaux télévisés : Audiovisual segmentation and identification of persons in broadcast news.” 2015. Web. 25 Jan 2021.

Vancouver:

Gay P. Segmentation et identification audiovisuelle de personnes dans des journaux télévisés : Audiovisual segmentation and identification of persons in broadcast news. [Internet] [Doctoral dissertation]. Le Mans; 2015. [cited 2021 Jan 25]. Available from: http://www.theses.fr/2015LEMA1021.

Council of Science Editors:

Gay P. Segmentation et identification audiovisuelle de personnes dans des journaux télévisés : Audiovisual segmentation and identification of persons in broadcast news. [Doctoral Dissertation]. Le Mans; 2015. Available from: http://www.theses.fr/2015LEMA1021

NSYSU

15. Chen, Shih-hsiung. A Multilevel Analysis of the Moderated Mediation Effect on Organizational Identification between Person-Organization fit and Turnover Intention.

Degree: PhD, Human Resource Management, 2016, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0417116-081807

► The main purpose of this study is to examine the influence of individual employeesâ P-O fit on their organization identification and turnover intention by applying… (more)

Subjects/Keywords: turnover intention; organization identification; difference score; cross-culture comparison; person-organization fit; multilevel analysis

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Chen, S. (2016). A Multilevel Analysis of the Moderated Mediation Effect on Organizational Identification between Person-Organization fit and Turnover Intention. (Doctoral Dissertation). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0417116-081807

Chicago Manual of Style (16^th Edition):

Chen, Shih-hsiung. “A Multilevel Analysis of the Moderated Mediation Effect on Organizational Identification between Person-Organization fit and Turnover Intention.” 2016. Doctoral Dissertation, NSYSU. Accessed January 25, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0417116-081807.

MLA Handbook (7^th Edition):

Chen, Shih-hsiung. “A Multilevel Analysis of the Moderated Mediation Effect on Organizational Identification between Person-Organization fit and Turnover Intention.” 2016. Web. 25 Jan 2021.

Vancouver:

Chen S. A Multilevel Analysis of the Moderated Mediation Effect on Organizational Identification between Person-Organization fit and Turnover Intention. [Internet] [Doctoral dissertation]. NSYSU; 2016. [cited 2021 Jan 25]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0417116-081807.

Council of Science Editors:

Chen S. A Multilevel Analysis of the Moderated Mediation Effect on Organizational Identification between Person-Organization fit and Turnover Intention. [Doctoral Dissertation]. NSYSU; 2016. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0417116-081807

Queensland University of Technology

16. Bialkowski, Alina Natalia. Aligning and characterising group behaviours using role information.

Degree: 2015, Queensland University of Technology

URL: https://eprints.qut.edu.au/86706/

► Techniques to align spatio-temporal data for large-scale analysis of human group behaviour have been developed. Application of the techniques to sports databases enable sport team's… (more)

Subjects/Keywords: Group behaviour; Formation; Roles; Alignment; Sports Analytics; Soccer; Person Re-Identification; Surveillance

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Bialkowski, A. N. (2015). Aligning and characterising group behaviours using role information. (Thesis). Queensland University of Technology. Retrieved from https://eprints.qut.edu.au/86706/

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Bialkowski, Alina Natalia. “Aligning and characterising group behaviours using role information.” 2015. Thesis, Queensland University of Technology. Accessed January 25, 2021. https://eprints.qut.edu.au/86706/.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Bialkowski, Alina Natalia. “Aligning and characterising group behaviours using role information.” 2015. Web. 25 Jan 2021.

Vancouver:

Bialkowski AN. Aligning and characterising group behaviours using role information. [Internet] [Thesis]. Queensland University of Technology; 2015. [cited 2021 Jan 25]. Available from: https://eprints.qut.edu.au/86706/.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Bialkowski AN. Aligning and characterising group behaviours using role information. [Thesis]. Queensland University of Technology; 2015. Available from: https://eprints.qut.edu.au/86706/

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Vilnius University

17. Kranauskas, Justas. Person Identification by Face and Iris.

Degree: Dissertation, Informatics, 2010, Vilnius University

URL: http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2010~D_20100213_102103-34345 ;

►

In this thesis, person identification by combining automatic face and iris recognition is analyzed. Person identification by his face is one of the most intuitive… (more)

▼

In this thesis, person identification by combining automatic face and iris recognition is analyzed. Person identification by his face is one of the most intuitive from all biometric measures. We are used to recognizing familiar faces and confirming identity by a short glance at one's id card which contains image of the face. We are also used to being observed by surveillance cameras, which can perform biometric authentication without even being noticed. However, facial biometrics is one of most unstable metrics because the face gets noticeably older in several years and can frequently change depending on the mood of its owner. The core algorithm for facial recognition presented in this work is based on Gabor features. Deep analysis of each step helped to develop the method with better or similar accuracy to the best published results received on the same datasets, while being simple and fast. On the other hand, person identification by his iris is one of the most sophisticated, stable and accurate biometrics. The core algorithm for iris recognition presented in this work is based on a novel iris texture representation by local extremum points of multiscale Taylor expansion. The proposed irises comparison method is very different from the classic phase-based methods, but is also fast and accurate. Combining it with our implementation of phase-based method results in superior recognition accuracy which is comparable or better than any published results received on the same... [to full text]

Darbe tyrinėjama asmens identifikacija, kombinuojant automatinį veido ir akies rainelės atpažinimą. Automatinė identifikacija pagal veidą yra intuityviausia iš biometrijos metrikų, kadangi būtent pagal veidą mes geriausiai sugebame atpažinti pažįstamus asmenis. Tai yra ir viena labiausiai priimtinų, kadangi visi esame įprate, kad mus filmuoja apsaugos kameros, lengviausiai išmatuojama - nes nereikalauja jokių įmantrių skanerių, tačiau kartu - tai yra ir viena iš nestabiliausių metrikų, kadangi veidas sensta ir šiaip kinta priklausomai nuo savininko nuotaikos. Darbe pristatomas veidų atpažinimo algoritmas paremtas Gaboro požymiais. Nuodugni analizė padėjo sukurti algoritmą, kurio tikslumą vertinant standartiniais testais jis lenkia arba yra lygus su geriausiais publikuotais metodais, tačiau pasižymi paprastumu ir dideliu greičiu. Tuo tarpu automatinė identifikacija pagal rainelę yra laikoma viena stabiliausių ir tiksliausių. Darbe pristatomas rainelių atpažinimo algoritmas naudoja naujovišką rainelių tekstūros vaizdavimo būdą, paremtą lokaliais dvimačiais funkcijų aproksimacijos Teiloro eilutėmis ekstremumais. Kartu pristatomas naudojamų požymių palyginimo metodas, kuris yra labai nutolęs nuo bet kokių iki šiol rainelių tekstūrų palyginimui naudojamų metodų. Pasiūlytas rainelių atpažinimo metodas vėlgi yra spartus ir itin tikslus, o sujungus su klasikinio stiliaus rainelių tekstūrų palyginimu tikslumu nenusileidžia geriausiems publikuotiems metodams. Darbas užbaigiamas veidų... [toliau žr. visą tekstą]

Advisors/Committee Members: Bastys, Algirdas (Doctoral dissertation supervisor), Ivanauskas, Feliksas (Doctoral dissertation committee chair), Juozapavičius, Algimantas (Doctoral dissertation committee member), Kleiza, Vytautas (Doctoral dissertation committee member), Raudys, Šarūnas (Doctoral dissertation committee member), Telksnys, Laimutis (Doctoral dissertation committee member), Punys, Jonas (Doctoral dissertation opponent), Vaicekauskas, Rimantas (Doctoral dissertation opponent).

Subjects/Keywords: Person identification; Face recognition; Iris recognition; Asmens identifikavimas; Atpažinimas pagal veidą; Atpažinimas pagal rainelę

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Kranauskas, J. (2010). Person Identification by Face and Iris. (Doctoral Dissertation). Vilnius University. Retrieved from http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2010~D_20100213_102103-34345 ;

Chicago Manual of Style (16^th Edition):

Kranauskas, Justas. “Person Identification by Face and Iris.” 2010. Doctoral Dissertation, Vilnius University. Accessed January 25, 2021. http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2010~D_20100213_102103-34345 ;.

MLA Handbook (7^th Edition):

Kranauskas, Justas. “Person Identification by Face and Iris.” 2010. Web. 25 Jan 2021.

Vancouver:

Kranauskas J. Person Identification by Face and Iris. [Internet] [Doctoral dissertation]. Vilnius University; 2010. [cited 2021 Jan 25]. Available from: http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2010~D_20100213_102103-34345 ;.

Council of Science Editors:

Kranauskas J. Person Identification by Face and Iris. [Doctoral Dissertation]. Vilnius University; 2010. Available from: http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2010~D_20100213_102103-34345 ;

Vilnius University

18. Kranauskas, Justas. Asmens identifikavimas pagal veidą ir akies rainelę.

Degree: PhD, Informatics, 2010, Vilnius University

URL: http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2010~D_20100213_102112-81518 ;

►

Darbe tyrinėjama asmens identifikacija, kombinuojant automatinį veido ir akies rainelės atpažinimą. Automatinė identifikacija pagal veidą yra intuityviausia iš biometrijos metrikų, kadangi būtent pagal veidą mes… (more)

▼

Darbe tyrinėjama asmens identifikacija, kombinuojant automatinį veido ir akies rainelės atpažinimą. Automatinė identifikacija pagal veidą yra intuityviausia iš biometrijos metrikų, kadangi būtent pagal veidą mes geriausiai sugebame atpažinti pažįstamus asmenis. Tai yra ir viena labiausiai priimtinų, kadangi visi esame įprate, kad mus filmuoja apsaugos kameros, lengviausiai išmatuojama - nes nereikalauja jokių įmantrių skanerių, tačiau kartu - tai yra ir viena iš nestabiliausių metrikų, kadangi veidas sensta ir šiaip kinta priklausomai nuo savininko nuotaikos. Darbe pristatomas veidų atpažinimo algoritmas paremtas Gaboro požymiais. Nuodugni analizė padėjo sukurti algoritmą, kurio tikslumą vertinant standartiniais testais jis lenkia arba yra lygus su geriausiais publikuotais metodais, tačiau pasižymi paprastumu ir dideliu greičiu. Tuo tarpu automatinė identifikacija pagal rainelę yra laikoma viena stabiliausių ir tiksliausių. Darbe pristatomas rainelių atpažinimo algoritmas naudoja naujovišką rainelių tekstūros vaizdavimo būdą, paremtą lokaliais dvimačiais funkcijų aproksimacijos Teiloro eilutėmis ekstremumais. Kartu pristatomas naudojamų požymių palyginimo metodas, kuris yra labai nutolęs nuo bet kokių iki šiol rainelių tekstūrų palyginimui naudojamų metodų. Pasiūlytas rainelių atpažinimo metodas vėlgi yra spartus ir itin tikslus, o sujungus su klasikinio stiliaus rainelių tekstūrų palyginimu tikslumu nenusileidžia geriausiems publikuotiems metodams. Darbas užbaigiamas veidų... [toliau žr. visą tekstą]

In this thesis, person identification by combining automatic face and iris recognition is analyzed. Person identification by his face is one of the most intuitive from all biometric measures. We are used to recognizing familiar faces and confirming identity by a short glance at one's id card which contains image of the face. We are also used to being observed by surveillance cameras, which can perform biometric authentication without even being noticed. However, facial biometrics is one of most unstable metrics because the face gets noticeably older in several years and can frequently change depending on the mood of its owner. The core algorithm for facial recognition presented in this work is based on Gabor features. Deep analysis of each step helped to develop the method with better or similar accuracy to the best published results received on the same datasets, while being simple and fast. On the other hand, person identification by his iris is one of the most sophisticated, stable and accurate biometrics. The core algorithm for iris recognition presented in this work is based on a novel iris texture representation by local extremum points of multiscale Taylor expansion. The proposed irises comparison method is very different from the classic phase-based methods, but is also fast and accurate. Combining it with our implementation of phase-based method results in superior recognition accuracy which is comparable or better than any published results received on the same... [to full text]

Advisors/Committee Members: Bastys, Algirdas (Doctoral dissertation supervisor), Ivanauskas, Feliksas (Doctoral dissertation committee chair), Juozapavičius, Algimantas (Doctoral dissertation committee member), Kleiza, Vytautas (Doctoral dissertation committee member), Raudys, Šarūnas (Doctoral dissertation committee member), Telksnys, Laimutis (Doctoral dissertation committee member), Punys, Jonas (Doctoral dissertation opponent), Vaicekauskas, Rimantas (Doctoral dissertation opponent).

Subjects/Keywords: Asmens identifikavimas; Atpažinimas pagal veidą; Atpažinimas pagal rainelę; Person identification; Face recognition; Iris recognition

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Kranauskas, J. (2010). Asmens identifikavimas pagal veidą ir akies rainelę. (Doctoral Dissertation). Vilnius University. Retrieved from http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2010~D_20100213_102112-81518 ;

Chicago Manual of Style (16^th Edition):

Kranauskas, Justas. “Asmens identifikavimas pagal veidą ir akies rainelę.” 2010. Doctoral Dissertation, Vilnius University. Accessed January 25, 2021. http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2010~D_20100213_102112-81518 ;.

MLA Handbook (7^th Edition):

Kranauskas, Justas. “Asmens identifikavimas pagal veidą ir akies rainelę.” 2010. Web. 25 Jan 2021.

Vancouver:

Kranauskas J. Asmens identifikavimas pagal veidą ir akies rainelę. [Internet] [Doctoral dissertation]. Vilnius University; 2010. [cited 2021 Jan 25]. Available from: http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2010~D_20100213_102112-81518 ;.

Council of Science Editors:

Kranauskas J. Asmens identifikavimas pagal veidą ir akies rainelę. [Doctoral Dissertation]. Vilnius University; 2010. Available from: http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2010~D_20100213_102112-81518 ;

Northeastern University

19. Gou, Mengran. The empirical moment matrix and its application in computer vision.

Degree: PhD, Department of Electrical and Computer Engineering, 2018, Northeastern University

URL: http://hdl.handle.net/2047/D20291232

► Embedding local properties of an image, for instance its color intensities or the magnitude and orientation of its gradients, to create a representative feature is… (more)

▼ Embedding local properties of an image, for instance its color intensities or the magnitude and orientation of its gradients, to create a representative feature is a critical component in many computer vision tasks, such as detection, classification, segmentation and tracking. A feature that is representative yet invariant to nuisance factors will scaffold the following modules in the processing pipeline and lead to a better performance for the task at hand. Statistical moments have often been utilized to build such descriptors since they provide a quantitative measure for the shape of the underlying distribution of the data. Examples of these include the covariance matrix feature, bilinear pooling encoding and Gaussian descriptors. However, until now, these features have been limited to using up to second order moments, i.e. the mean and variance of the data, and hence can be poor descriptors when the underlying distribution is non-Gaussian. This dissertation aims towards examining this problem in-depth and identifying possible solutions. In particular, we propose to use feature descriptors based on the empirical moment matrix, which gathers high order moments and embeds them into the manifold of symmetric positive definite (SPD) matrices. The effectiveness of the proposed approach is illustrated in the context of two computer vision problems: person re-Identification (re-ID) and fine-grain classification.; Person re-ID is the problem of matching images of a pedestrian across cameras with no overlapping fields of view. It is one of the key tasks in surveillance video processing. Yet, due to the extremely large inter-class variances across different cameras (e.g., poses, illumination, viewpoints), the performance of the state-of-the-art person re-id algorithms is still far from ideal. In this thesis, we propose a novel descriptor, based on the on-manifold mean of a moment matrix (moM) and horizontal mean pooling, which can be used to approximate complex, non-Gaussian, distributions of the pixel features within a mid-sized local patch. To mitigate the gap between academic research and real-world applications, two large-scale public re-ID datasets are proposed and a systematic benchmark evaluation is established on both new datasets. Extensive experiments on five widely used public re-ID datasets and two newly collected datasets demonstrate that incorporating the proposed moM feature improves re-ID performance.; Different from general objection recognition tasks, fine-grained classification usually tries to distinguish objects at the sub-category level, such as different makes of cars or different species of a bird. The main challenge of this task is the relatively large inter-class and relatively small intra-class variations. The most successful approaches to this problem use deep convolutional neural network(CNN), where the top convolutional layers perform a local representation extraction step and the bottom fully connected layers perform an encoding step. In the case of fine-grain classification, bilinear pooling…

Subjects/Keywords: computer vision; empirical moment; feature encoding; feature extraction; fine-grained classification; person re-identification

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Gou, M. (2018). The empirical moment matrix and its application in computer vision. (Doctoral Dissertation). Northeastern University. Retrieved from http://hdl.handle.net/2047/D20291232

Chicago Manual of Style (16^th Edition):

Gou, Mengran. “The empirical moment matrix and its application in computer vision.” 2018. Doctoral Dissertation, Northeastern University. Accessed January 25, 2021. http://hdl.handle.net/2047/D20291232.

MLA Handbook (7^th Edition):

Gou, Mengran. “The empirical moment matrix and its application in computer vision.” 2018. Web. 25 Jan 2021.

Vancouver:

Gou M. The empirical moment matrix and its application in computer vision. [Internet] [Doctoral dissertation]. Northeastern University; 2018. [cited 2021 Jan 25]. Available from: http://hdl.handle.net/2047/D20291232.

Council of Science Editors:

Gou M. The empirical moment matrix and its application in computer vision. [Doctoral Dissertation]. Northeastern University; 2018. Available from: http://hdl.handle.net/2047/D20291232

Queen Mary, University of London

20. Wang, Hanxiao. Minimising human annotation for scalable person re-identification.

Degree: PhD, 2017, Queen Mary, University of London

URL: http://qmro.qmul.ac.uk/xmlui/handle/123456789/30884 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.766051

► Among the diverse tasks performed by an intelligent distributed multi-camera surveillance system, person re-identification (re-id) is one of the most essential. Re-id refers to associating… (more)

▼ Among the diverse tasks performed by an intelligent distributed multi-camera surveillance system, person re-identification (re-id) is one of the most essential. Re-id refers to associating an individual or a group of people across non-overlapping cameras at different times and locations, and forms the foundation of a variety of applications ranging from security and forensic search to quotidian retail and health care. Though attracted rapidly increasing academic interests over the past decade, it still remains a non-trivial and unsolved problem for launching a practical reid system in real-world environments, due to the ambiguous and noisy feature of surveillance data and the potentially dramatic visual appearance changes caused by uncontrolled variations in human poses and divergent viewing conditions across distributed camera views. To mitigate such visual ambiguity and appearance variations, most existing re-id approaches rely on constructing fully supervised machine learning models with extensively labelled training datasets which is unscalable for practical applications in the real-world. Particularly, human annotators must exhaustively search over a vast quantity of offline collected data, manually label cross-view matched images of a large population between every possible camera pair. Nonetheless, having the prohibitively expensive human efforts dissipated, a trained re-id model is often not easily generalisable and transferable, due to the elastic and dynamic operating conditions of a surveillance system. With such motivations, this thesis proposes several scalable re-id approaches with significantly reduced human supervision, readily applied to practical applications. More specifically, this thesis has developed and investigated four new approaches for reducing human labelling effort in real-world re-id as follows: Chapter 3 The first approach is affinity mining from unlabelled data. Different from most existing supervised approaches, this work aims to model the discriminative information for reid without exploiting human annotations, but from the vast amount of unlabelled person image data, thus applicable to both semi-supervised and unsupervised re-id. It is non-trivial since the human annotated identity matching correspondence is often the key to discriminative re-id modelling. In this chapter, an alternative strategy is explored by specifically mining two types of affinity relationships among unlabelled data: (1) inter-view data affinity and (2) intra-view data affinity. In particular, with such affinity information encoded as constraints, a Regularised Kernel Subspace Learning model is developed to explicitly reduce inter-view appearance variations and meanwhile enhance intra-view appearance disparity for more discriminative re-id matching. Consequently, annotation costs can be immensely alleviated and a scalable re-id model is readily to be leveraged to plenty of unlabelled data which is inexpensive to collect. Chapter 4 The second approach is saliency discovery from unlabelled data. This chapter…

Subjects/Keywords: Electronic Engineering and Computer Science; person re-identification; Surveillance systems; machine learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Wang, H. (2017). Minimising human annotation for scalable person re-identification. (Doctoral Dissertation). Queen Mary, University of London. Retrieved from http://qmro.qmul.ac.uk/xmlui/handle/123456789/30884 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.766051

Chicago Manual of Style (16^th Edition):

Wang, Hanxiao. “Minimising human annotation for scalable person re-identification.” 2017. Doctoral Dissertation, Queen Mary, University of London. Accessed January 25, 2021. http://qmro.qmul.ac.uk/xmlui/handle/123456789/30884 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.766051.

MLA Handbook (7^th Edition):

Wang, Hanxiao. “Minimising human annotation for scalable person re-identification.” 2017. Web. 25 Jan 2021.

Vancouver:

Wang H. Minimising human annotation for scalable person re-identification. [Internet] [Doctoral dissertation]. Queen Mary, University of London; 2017. [cited 2021 Jan 25]. Available from: http://qmro.qmul.ac.uk/xmlui/handle/123456789/30884 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.766051.

Council of Science Editors:

Wang H. Minimising human annotation for scalable person re-identification. [Doctoral Dissertation]. Queen Mary, University of London; 2017. Available from: http://qmro.qmul.ac.uk/xmlui/handle/123456789/30884 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.766051

Loughborough University

21. Aburasain, Rua. Application of convolutional neural networks in object detection, re-identification and recognition.

Degree: PhD, 2020, Loughborough University

URL: https://doi.org/10.26174/thesis.lboro.13014005.v1 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.816233

► This thesis investigates the effective deployment of deep Convolutional Neural Networks (CNNs) architectures in two different application areas for security and surveillance purposes, namely person… (more)

▼ This thesis investigates the effective deployment of deep Convolutional Neural Networks (CNNs) architectures in two different application areas for security and surveillance purposes, namely person re-identification and aerial, large-scale, object detection and recognition, in which the data capture sources are cameras within CCTV systems and on-board drones, respectively. First of all, person re-identification is of significance importance in video surveillance applications and remains an open research problem to-date. A significant research effort has been focused worldwide in this area, where initially traditional machine learning approaches were used as the technology that underpins the person re-identification, but in the recent past with the advent of significant developments in Deep Neural Network (DNN) technology, several efforts have been made in using DNNs in person re-identification. Unfortunately, all such attempts have been limited to using a selected CNN in person re-identification associated with a single dataset, mostly those available in the public domain. Furthermore, such attempts are very limited in their analysis of the potential to optimise such networks for use within a given dataset. In this thesis we therefore conduct a comprehensive investigation on the effectiveness of the use of the state-of-the-art CNN meta-architectures, AlexNet, VGGNet-16, ResNet and Inception V4, in seven benchmark person re-identification datasets. The impact of tuning the learning rate of the networks and the optimization methods, are evaluated, with the aim of optimising the object re-identification accuracy. This research proves the significance of the network hyper-parameter optimisation besides the importance of data preparation, training, testing and evaluation to obtain the optimum performance of a given network when applied to a specific dataset. The rigorous investigations carried out in this thesis and the conclusions thus made closes a significant current research gap in both the effective use of DNN technology, generally in any application and specifically in person re-identification. The second part of this thesis focuses on the effective use of DNN technology in efficient object detection, in drone-based imagery. In this modern era, drones facilitate accessing images in challenging environments and scanning large ground/terrain areas in a minimum time, which enables many new applications to be established based on automatic computer-based analysis of drone imagery. As drones are typically flown at high altitudes in order to facilitate coverage of large areas within a short time, the captured object size tends to be very small and mostly very low in resolution, thus poses a significant challenge in using drone-imagery for object detection and recognition. The use of traditional machine learning approaches for object detection in drone imagery will thus be very restrictive. However, the latest developments in DNN technology provides hope for the development of object detectors for drone imagery.…

Subjects/Keywords: Drones; Convolutional Neural Networks Imaging; object detection algorithms; Person re-identification; Unmanned arial Vehicle

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Aburasain, R. (2020). Application of convolutional neural networks in object detection, re-identification and recognition. (Doctoral Dissertation). Loughborough University. Retrieved from https://doi.org/10.26174/thesis.lboro.13014005.v1 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.816233

Chicago Manual of Style (16^th Edition):

Aburasain, Rua. “Application of convolutional neural networks in object detection, re-identification and recognition.” 2020. Doctoral Dissertation, Loughborough University. Accessed January 25, 2021. https://doi.org/10.26174/thesis.lboro.13014005.v1 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.816233.

MLA Handbook (7^th Edition):

Aburasain, Rua. “Application of convolutional neural networks in object detection, re-identification and recognition.” 2020. Web. 25 Jan 2021.

Vancouver:

Aburasain R. Application of convolutional neural networks in object detection, re-identification and recognition. [Internet] [Doctoral dissertation]. Loughborough University; 2020. [cited 2021 Jan 25]. Available from: https://doi.org/10.26174/thesis.lboro.13014005.v1 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.816233.

Council of Science Editors:

Aburasain R. Application of convolutional neural networks in object detection, re-identification and recognition. [Doctoral Dissertation]. Loughborough University; 2020. Available from: https://doi.org/10.26174/thesis.lboro.13014005.v1 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.816233

22. Padilla López, José Ramón. Protección de la Privacidad Visual basada en el Reconocimiento del Contexto .

Degree: 2015, University of Alicante

URL: http://hdl.handle.net/10045/52056

► En la actualidad, la cámara de vídeo se ha convertido en un dispositivo omnipresente. Debido a su miniaturización, estas se pueden encontrar integradas en multitud… (more)

▼ En la actualidad, la cámara de vídeo se ha convertido en un dispositivo omnipresente. Debido a su miniaturización, estas se pueden encontrar integradas en multitud de dispositivos de uso diario, desde teléfonos móviles o tabletas, hasta ordenadores portátiles. Aunque estos dispositivos son empleados por millones de personas diariamente de forma inofensiva, capturando vídeo, realizando fotografías que luego son compartidas, etc.; el empleo de videocámaras para tareas de videovigilancia levanta cierta preocupación entre la población, sobre todo cuando estas forman parte de sistemas inteligentes de monitorización. Esto supone una amenaza para la privacidad debido a que las grabaciones realizadas por estos sistemas contienen una gran cantidad de información que puede ser extraída de forma automática mediante técnicas de visión artificial. Sin embargo, la aplicación de esta tecnología en diversas áreas puede suponer un impacto muy positivo para las personas. Por otro lado, la población mundial está envejeciendo rápidamente. Este cambio demográfico provocará que un mayor número de personas en situación de dependencia, o que requieren apoyo en su vida diaria, vivan solas. Por lo que se hace necesario encontrar una solución que permita extender su autonomía. La vida asistida por el entorno (AAL por sus siglas en inglés) ofrece una solución aportando inteligencia al entorno donde residen la personas de modo que este les asista en sus actividades diarias. Estos entornos requieren la instalación de sensores para la captura de datos. La utilización de videocámaras, con la riqueza en los datos que ofrecen, en entornos privados haría posible la creación de servicios AAL orientados hacia el cuidado de las personas como, por ejemplo, la detección de accidentes en el hogar, detección temprana de problemas cognitivos y muchos otros. Sin embargo, dada la sencilla interpretación de imágenes por las personas, esto plantea problemas éticos que afectan a la privacidad. En este trabajo se propone una solución para poder hacer uso de videocámaras en entornos privados con el objetivo de dar soporte a las personas y habilitar así el desarrollo de servicios de la vida asistida por el entorno en un hogar inteligente. En concreto, se propone la protección de la privacidad en aquellos servicios AAL de monitorización que requieren acceso al vídeo por parte de un cuidador, ya sea profesional o informal. Esto sucede, por ejemplo, cuando se detecta un accidente en un sistema de monitorización y ese evento requiere la confirmación visual de lo ocurrido. Igualmente, en servicios AAL de telerehabilitación puede ser requerida la supervisión por parte de un humano. En este tipo de escenarios es fundamental proteger la privacidad en el momento en que se esté accediendo u observando el vídeo. Como parte de este trabajo se ha llevado a cabo el estudio del estado de la cuestión en la cual se han revisado los métodos de protección de la privacidad visual presentes en la literatura. Esta revisión es la primera en realizar un análisis exhaustivo de este tema… Advisors/Committee Members: Flórez-Revuelta, Francisco (advisor).

Subjects/Keywords: Privacy protection; Context aware; Human action recognition; Person re-identification; Computer vision; Ambient-assisted living

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Padilla López, J. R. (2015). Protección de la Privacidad Visual basada en el Reconocimiento del Contexto . (Thesis). University of Alicante. Retrieved from http://hdl.handle.net/10045/52056

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Padilla López, José Ramón. “Protección de la Privacidad Visual basada en el Reconocimiento del Contexto .” 2015. Thesis, University of Alicante. Accessed January 25, 2021. http://hdl.handle.net/10045/52056.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Padilla López, José Ramón. “Protección de la Privacidad Visual basada en el Reconocimiento del Contexto .” 2015. Web. 25 Jan 2021.

Vancouver:

Padilla López JR. Protección de la Privacidad Visual basada en el Reconocimiento del Contexto . [Internet] [Thesis]. University of Alicante; 2015. [cited 2021 Jan 25]. Available from: http://hdl.handle.net/10045/52056.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Padilla López JR. Protección de la Privacidad Visual basada en el Reconocimiento del Contexto . [Thesis]. University of Alicante; 2015. Available from: http://hdl.handle.net/10045/52056

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Maryland

23. Ahmed, Ejaz. Understanding Objects in the Visual World.

Degree: Computer Science, 2015, University of Maryland

URL: http://hdl.handle.net/1903/16684

► One way to understand the visual world is by reasoning about the objects present in it: their type, their location, their similarities, their layout etc.… (more)

▼ One way to understand the visual world is by reasoning about the objects present in it: their type, their location, their similarities, their layout etc. Despite several successes, detailed recognition remains a challenging tasks for current computer vision systems. This dissertation focuses on building systems that improve on the state-of-the-art on several fronts. On one hand, we propose better representations of visual categories that enable more accurate reasoning about their properties. To learn such representations, we employ machine learning methods that leverage the power of big-data. On the other hand, we present solutions to make current frameworks more efficient without losing on performance. The first part of the dissertation focuses on improvements in efficiency. We first introduce a fast automated mechanism for selecting a diverse set of discriminative filters and show that one can efficiently learn a universal model of filter "goodness" based on properties of the filter itself. As an alternative to the expensive evaluation of filters, which is often the bottleneck in many techniques, our method has the potential of dramatically altering the trade-off between the accuracy of a filter based method and the cost of training. Second, we present a method for linear dimensionality reduction which we call composite discriminant factor analysis (CDF). CDF searches for a discriminative but compact feature subspace in which the classifiers can be trained, leading to an order of magnitude saving in detection time. In the second part, we focus on the problem of person re-identification, an important component of surveillance systems. We present a deep learning architecture that simultaneously learns features and computes their corresponding similarity metric. Given a pair of images as input, our network outputs a similarity value indicating whether the two input images depict the same person. We propose new layers which capture local relationships among mid-level features, produce a high-level summary of these relationships and spatially integrate them to give a holistic representation. In the final part, we present a semantic object selection framework that uses natural language input to perform image editing. In the general context of interactive object segmentation, many of the methods that utilize user input (such as mouse clicks and mouse strokes) often require significant user intervention. In this work, we present a system with a far simpler input method: the user only needs to give the name of the desired object. For this problem we present a solution which borrows ideas from image retrieval, segmentation propagation, object localization and convolution neural networks. Advisors/Committee Members: Davis, Larry S (advisor).

Subjects/Keywords: Computer science; Computer Vision; Deep Learning; Filter Selection; Object Detection; Object Selection; Person Re-Identification

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Ahmed, E. (2015). Understanding Objects in the Visual World. (Thesis). University of Maryland. Retrieved from http://hdl.handle.net/1903/16684

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Ahmed, Ejaz. “Understanding Objects in the Visual World.” 2015. Thesis, University of Maryland. Accessed January 25, 2021. http://hdl.handle.net/1903/16684.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Ahmed, Ejaz. “Understanding Objects in the Visual World.” 2015. Web. 25 Jan 2021.

Vancouver:

Ahmed E. Understanding Objects in the Visual World. [Internet] [Thesis]. University of Maryland; 2015. [cited 2021 Jan 25]. Available from: http://hdl.handle.net/1903/16684.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Ahmed E. Understanding Objects in the Visual World. [Thesis]. University of Maryland; 2015. Available from: http://hdl.handle.net/1903/16684

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Cambridge

24. Pfeil, Katrin. The effectiveness of the Self-Administered Interview© : a meta-analytic review and empirical study with older adult witnesses.

Degree: PhD, 2018, University of Cambridge

URL: https://doi.org/10.17863/CAM.22056 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744685

► The Self-Administered Interview© (SAI©) is an eyewitness interviewing tool designed to help protect eyewitness memory and elicit a comprehensive initial statement (Gabbert, Hope, & Fisher,… (more)

▼ The Self-Administered Interview© (SAI©) is an eyewitness interviewing tool designed to help protect eyewitness memory and elicit a comprehensive initial statement (Gabbert, Hope, & Fisher, 2009). Early research shows promising results in general adult samples. Whether the SAI© is an effective tool for older adult witnesses has not yet been fully addressed. Older adults will become increasingly important as a witness population in the future, yet perform worse compared to young adults. Some attempts have been made to aid older adult witnesses, but an easy-to-apply and effective method is yet to be introduced. This dissertation presents an overview of current knowledge on eyewitnesses and provides a theoretical basis for the empirical chapters. It further presents results of a systematic review and several meta-analyses on the effectiveness of the SAI© as a means to enhance eyewitness testimony. The meta-analyses cover 38 experimental comparisons from 22 empirical studies representing 1712 interviewees. Results indicate a strong benefit of the SAI both immediately after the witnessed crime (d = 1.20) and in a delayed recall (d = 0.92 compared to no initial recall) after one to three weeks. The third large chapter of this dissertation presents the results of an experiment that investigated the effectiveness of the SAI© for older witnesses’ testimony, suggestibility and lineup performance. 144 participants, half of which were 60 years or older and half aged 18-30 years, took part in two sessions. In the first session, they were shown a film of a staged crime and either filled in the SAI©, gave a written free recall or no initial recall. In the second session after one week they were then asked to give a free recall of what they remembered, answer questions including suggestive questions, and also to identify the perpetrator from the film from a 6-person simultaneous photo lineup. Results confirm the classic SAI© effect for young adults, show a small beneficial effect for older adults and also indicate a beneficial effect for lineup performance for the first time.

Subjects/Keywords: 363.25; Eyewitnesses; Investigative Interviewing; Meta-Analysis; Self-Administered Interview; Testimony; Person Identification

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Pfeil, K. (2018). The effectiveness of the Self-Administered Interview© : a meta-analytic review and empirical study with older adult witnesses. (Doctoral Dissertation). University of Cambridge. Retrieved from https://doi.org/10.17863/CAM.22056 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744685

Chicago Manual of Style (16^th Edition):

Pfeil, Katrin. “The effectiveness of the Self-Administered Interview© : a meta-analytic review and empirical study with older adult witnesses.” 2018. Doctoral Dissertation, University of Cambridge. Accessed January 25, 2021. https://doi.org/10.17863/CAM.22056 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744685.

MLA Handbook (7^th Edition):

Pfeil, Katrin. “The effectiveness of the Self-Administered Interview© : a meta-analytic review and empirical study with older adult witnesses.” 2018. Web. 25 Jan 2021.

Vancouver:

Pfeil K. The effectiveness of the Self-Administered Interview© : a meta-analytic review and empirical study with older adult witnesses. [Internet] [Doctoral dissertation]. University of Cambridge; 2018. [cited 2021 Jan 25]. Available from: https://doi.org/10.17863/CAM.22056 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744685.

Council of Science Editors:

Pfeil K. The effectiveness of the Self-Administered Interview© : a meta-analytic review and empirical study with older adult witnesses. [Doctoral Dissertation]. University of Cambridge; 2018. Available from: https://doi.org/10.17863/CAM.22056 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744685

University of Georgia

25. Jafri, Rabia. Fusion of face and gait for human recognition.

Degree: 2014, University of Georgia

URL: http://hdl.handle.net/10724/24940

► A system that integrates the face, a physical biometric, with gait, a behavioral biometric, for automatically recognizing human beings effectively under a wider range of… (more)

▼ A system that integrates the face, a physical biometric, with gait, a behavioral biometric, for automatically recognizing human beings effectively under a wider range of conditions than a classifier which exclusively employs only one of these biometrics, is proposed. A decision-level fusion approach is adopted where the top matches of the face classifier are passed on to the gait classifier which then determines the identity of the unknown person. For face recognition, a principle components analysis-based approach, as well as a Bayesian inference-based classifier is employed, while for gait recognition, a model-based strategy is implemented, which utilizes various gait features identified as being the most pertinent for recognition based on data collected using an optoelectronic motion capture system. The integrated system is found to outperform the individual face and gait classifiers that it is composed of, thus, demonstrating the potential of using the gait to supplement the face in scenarios where the face classifier alone does not perform well due to the non-availability of high resolution face data. During the course of this research, automated face recognition was also studied in detail, with a concentration on approaches that employ statistical dimensionality reduction techniques for this task. Experiments were conducted on some of the most widely-used methods in this category to test the recognition accuracy of these methods, and various combinations thereof, for different database sizes, images resolutions and number of bits per pixel. It was found that certain combinations of some of these techniques perform better than the individual methods that those combinations are comprised of when higher resolution face images are utilized. Furthermore, a system which utilizes different resolution versions of the whole face, as well as of various facial components, in a hierarchical manner was implemented and was found to achieve higher accuracy than its single-level counterpart which uses only the highest resolution images.

Subjects/Keywords: Face recognition; Gait recognition; Integrated face-gait recognition; Fusion of biometrics; Person identification

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Jafri, R. (2014). Fusion of face and gait for human recognition. (Thesis). University of Georgia. Retrieved from http://hdl.handle.net/10724/24940

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Jafri, Rabia. “Fusion of face and gait for human recognition.” 2014. Thesis, University of Georgia. Accessed January 25, 2021. http://hdl.handle.net/10724/24940.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Jafri, Rabia. “Fusion of face and gait for human recognition.” 2014. Web. 25 Jan 2021.

Vancouver:

Jafri R. Fusion of face and gait for human recognition. [Internet] [Thesis]. University of Georgia; 2014. [cited 2021 Jan 25]. Available from: http://hdl.handle.net/10724/24940.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Jafri R. Fusion of face and gait for human recognition. [Thesis]. University of Georgia; 2014. Available from: http://hdl.handle.net/10724/24940

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Pretoria

26. [No author]. A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians .

Degree: 2008, University of Pretoria

URL: http://upetd.up.ac.za/thesis/available/etd-11052008-172115/

► Since Schleiermacher, in nineteenth century, liberal theologians neglected the doctrine of the Trinity. However, on the basis of the Hegelian influence, leading 20th century theologians,… (more)

▼ Since Schleiermacher, in nineteenth century, liberal theologians neglected the doctrine of the Trinity. However, on the basis of the Hegelian influence, leading 20th century theologians, Barth, Moltmann, Jüngel and Pannenberg revitalized the doctrine of the Trinity. This revitalization was however based on a re-interpretation of the Nicene theology, in which vital elements of Nicene theology and its reformed affirmation were altered by their approach to the doctrine of the Trinity. Reformed doctrine of the Trinity is based on the Nicene formulation of the doctrine of the Trinity. In order to make a reformed assessment of this revitalization of the doctrine of the Trinity, one first has to attend to its Nicene formulation. Nicene theologians interpret the doctrine of the Trinity on the basis of the Scripture against heresies. Athanasius confirms not only the Son’s ‘homoousia’ with the Father, but also the Spirit’s homoousia with the Father. In this regard, Athanasius protects the deity of the Son and the Spirit. Basil and the two Gregories follow Athanasius. They also apply the term ‘homoousia’ to the Spirit. Especially, the Cappadocian theologians set the following formula of the doctrine of the Trinity: One essence, three hypostaseis. For them, according to the particularity of their attributes, the Father, the Son and the Holy Spirit are distinguished, however, according to their common essence, there is one God. Their main idea is that the three hypostaseis are equally God. They focus on the deity of the Son and the Holy Spirit against Arians and Pneumatomachians. They strongly emphasize the unity of nature or essence of God on the basis of the priority of theologia over economia. <ol> Karl Barth’s starting point is the revelation of God. For him the doctrine of the Trinity is three repetitions of God himself: Revealer, Revelation, and Revealedness. Barth identifies the the immanent Trinity with the economic Trinity. From this, his Christology always refers to the ensarkos Logos. And he uses the term ‘Seinsweise’ instead of the term ‘person’. For Moltmann, the content of the doctrine of the trinity is the crucifixion of Christ itself, and the form of the crucified one is the Trinity. He focuses on the passibility of God. He also identifies the immanent with the economic Trinity. His social understanding of the concept of divine Person is based on panentheism. As with Moltmann Jüngel concentrates on the ‘death of God’. For him, the theology of the death of God is based on Luther’s theology of the cross. The Christian doctrine of the triune God is the epitome of the story of Jesus Christ. With Barth and Moltmann he identifies the immanent Trinity with the economic Trinity. Pannenberg’s doctrine of the Trinity implies the divine self-disclosure in Jesus Christ. His Christology is ‘from below. And Pannenberg’s concept of person is the reciprocal relationship between persons.’ He confirms the identification of the immanent Trinity and economic Trinity. Modern understanding… Advisors/Committee Members: Prof C J Wethmar (advisor).

Subjects/Keywords: Trinity; Triune; Church; Immanent trinity; Filioque; Identification; Mission; Perichoresis; Person; Reciprocal relation; Ecclesiology; Economic trinity; UCTD

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

author], [. (2008). A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians . (Doctoral Dissertation). University of Pretoria. Retrieved from http://upetd.up.ac.za/thesis/available/etd-11052008-172115/

Chicago Manual of Style (16^th Edition):

author], [No. “A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians .” 2008. Doctoral Dissertation, University of Pretoria. Accessed January 25, 2021. http://upetd.up.ac.za/thesis/available/etd-11052008-172115/.

MLA Handbook (7^th Edition):

author], [No. “A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians .” 2008. Web. 25 Jan 2021.

Vancouver:

author] [. A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians . [Internet] [Doctoral dissertation]. University of Pretoria; 2008. [cited 2021 Jan 25]. Available from: http://upetd.up.ac.za/thesis/available/etd-11052008-172115/.

Council of Science Editors:

author] [. A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians . [Doctoral Dissertation]. University of Pretoria; 2008. Available from: http://upetd.up.ac.za/thesis/available/etd-11052008-172115/

UCLA

27. Karianakis, Nikolaos. Sampling Algorithms to Handle Nuisances in Large-Scale Recognition.

Degree: Computer Science, 2017, UCLA

URL: http://www.escholarship.org/uc/item/32t9r5b1

► Convolutional neural networks (CNNs) have risen to be the de-facto paragon for detecting the presence of objects in a scene, as portrayed by an image.… (more)

▼ Convolutional neural networks (CNNs) have risen to be the de-facto paragon for detecting the presence of objects in a scene, as portrayed by an image. CNNs are described as being "approximately invariant" to nuisance transformations such as planar translation, both by virtue of their convolutional architecture and by virtue of their approximation properties that, given sufficient parameters and training data, could in principle yield discriminants that are insensitive to nuisance transformations of the data. The fact that contemporary deep convolutional architectures appear very effective in classifying images as containing a given object regardless of its position, scale, and aspect ratio in large-scale benchmarks suggests that the network can effectively manage such nuisance variability. We conduct an empirical study and show that, contrary to popular belief, at the current level of complexity of convolutional architectures and scale of the data sets used to train them, CNNs are not very effective at marginalizing nuisance variability.This discovery leaves researchers the choice of investing more effort in the design of models that are less sensitive to nuisances or designing better region proposal algorithms in an effort to predict where the objects of interest lie and center the model around these regions. In this thesis steps towards both directions are made. First, we introduce DSP-CNN, which deploys domain-size pooling in order to transform the neural networks to be scale invariant in the convolutional operator level. Second, motivated by our empirical analysis, we propose novel sampling and pruning techniques for region proposal schemes that improve the end-to-end performance in large-scale classification, detection and wide-baseline correspondence to state-of-the-art levels. Additionally,since a proposal algorithm involves the design of a classifier, whose results are to be fed to another classifier (a Category CNN), it seems natural to leverage on the latter to design the former. Thus, we introduce a method that leverages on filters learned in the lower layers of CNNs to design a binary boosting classifier for generating class-agnostic proposals. Finally, we extend sampling over time by designing a temporal, hard-attention layer which is trained with reinforcement learning, with application in video sequences for person re-identification.

Subjects/Keywords: Computer science; Robotics; Electrical engineering; Convolutional Neural Networks; Deep Learning; Invariance; Nuisances; Object Proposals; Person Re-identification

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Karianakis, N. (2017). Sampling Algorithms to Handle Nuisances in Large-Scale Recognition. (Thesis). UCLA. Retrieved from http://www.escholarship.org/uc/item/32t9r5b1

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Karianakis, Nikolaos. “Sampling Algorithms to Handle Nuisances in Large-Scale Recognition.” 2017. Thesis, UCLA. Accessed January 25, 2021. http://www.escholarship.org/uc/item/32t9r5b1.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Karianakis, Nikolaos. “Sampling Algorithms to Handle Nuisances in Large-Scale Recognition.” 2017. Web. 25 Jan 2021.

Vancouver:

Karianakis N. Sampling Algorithms to Handle Nuisances in Large-Scale Recognition. [Internet] [Thesis]. UCLA; 2017. [cited 2021 Jan 25]. Available from: http://www.escholarship.org/uc/item/32t9r5b1.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Karianakis N. Sampling Algorithms to Handle Nuisances in Large-Scale Recognition. [Thesis]. UCLA; 2017. Available from: http://www.escholarship.org/uc/item/32t9r5b1

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Pretoria

28. Kim, Yong Jun. A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians.

Degree: Dogmatics and Christian Ethics, 2008, University of Pretoria

URL: http://hdl.handle.net/2263/29249

► Since Schleiermacher, in nineteenth century, liberal theologians neglected the doctrine of the Trinity. However, on the basis of the Hegelian influence, leading 20th century theologians,… (more)

▼ Since Schleiermacher, in nineteenth century, liberal theologians neglected the doctrine of the Trinity. However, on the basis of the Hegelian influence, leading 20th century theologians, Barth, Moltmann, Jüngel and Pannenberg revitalized the doctrine of the Trinity. This revitalization was however based on a re-interpretation of the Nicene theology, in which vital elements of Nicene theology and its reformed affirmation were altered by their approach to the doctrine of the Trinity. Reformed doctrine of the Trinity is based on the Nicene formulation of the doctrine of the Trinity. In order to make a reformed assessment of this revitalization of the doctrine of the Trinity, one first has to attend to its Nicene formulation. Nicene theologians interpret the doctrine of the Trinity on the basis of the Scripture against heresies. Athanasius confirms not only the Son’s ‘homoousia’ with the Father, but also the Spirit’s homoousia with the Father. In this regard, Athanasius protects the deity of the Son and the Spirit. Basil and the two Gregories follow Athanasius. They also apply the term ‘homoousia’ to the Spirit. Especially, the Cappadocian theologians set the following formula of the doctrine of the Trinity: One essence, three hypostaseis. For them, according to the particularity of their attributes, the Father, the Son and the Holy Spirit are distinguished, however, according to their common essence, there is one God. Their main idea is that the three hypostaseis are equally God. They focus on the deity of the Son and the Holy Spirit against Arians and Pneumatomachians. They strongly emphasize the unity of nature or essence of God on the basis of the priority of theologia over economia. <ol> Karl Barth’s starting point is the revelation of God. For him the doctrine of the Trinity is three repetitions of God himself: Revealer, Revelation, and Revealedness. Barth identifies the the immanent Trinity with the economic Trinity. From this, his Christology always refers to the ensarkos Logos. And he uses the term ‘Seinsweise’ instead of the term ‘person’. For Moltmann, the content of the doctrine of the trinity is the crucifixion of Christ itself, and the form of the crucified one is the Trinity. He focuses on the passibility of God. He also identifies the immanent with the economic Trinity. His social understanding of the concept of divine Person is based on panentheism. As with Moltmann Jüngel concentrates on the ‘death of God’. For him, the theology of the death of God is based on Luther’s theology of the cross. The Christian doctrine of the triune God is the epitome of the story of Jesus Christ. With Barth and Moltmann he identifies the immanent Trinity with the economic Trinity. Pannenberg’s doctrine of the Trinity implies the divine self-disclosure in Jesus Christ. His Christology is ‘from below. And Pannenberg’s concept of person is the reciprocal relationship between persons.’ He confirms the identification of the immanent Trinity and economic Trinity. Modern understanding… Advisors/Committee Members: Prof C J Wethmar (advisor).

Subjects/Keywords: Trinity; Triune; Church; Immanent trinity; Filioque; Identification; Mission; Perichoresis; Person; Reciprocal relation; Ecclesiology; Economic trinity; UCTD

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Kim, Y. J. (2008). A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians. (Doctoral Dissertation). University of Pretoria. Retrieved from http://hdl.handle.net/2263/29249

Chicago Manual of Style (16^th Edition):

Kim, Yong Jun. “A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians.” 2008. Doctoral Dissertation, University of Pretoria. Accessed January 25, 2021. http://hdl.handle.net/2263/29249.

MLA Handbook (7^th Edition):

Kim, Yong Jun. “A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians.” 2008. Web. 25 Jan 2021.

Vancouver:

Kim YJ. A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians. [Internet] [Doctoral dissertation]. University of Pretoria; 2008. [cited 2021 Jan 25]. Available from: http://hdl.handle.net/2263/29249.

Council of Science Editors:

Kim YJ. A reformed assessment of the revitalization of the doctrine of the Trinity by four leading twentienth century protestant theologians. [Doctoral Dissertation]. University of Pretoria; 2008. Available from: http://hdl.handle.net/2263/29249

University of Houston

29. Mantini, Pranav 1985-. Contextual Human Trajectory Forecasting within Indoor Environments and Its Applications.

Degree: PhD, Computer Science, 2015, University of Houston

URL: http://hdl.handle.net/10657/4880

► A human trajectory is the likely path a human subject would take to get to a destination. Human trajectory forecasting algorithms try to estimate or… (more)

Subjects/Keywords: Human trajectory forecasting; Human motion; Person re-identification; People tracking; Camera network; Camera placement; Human behavior

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Mantini, P. 1. (2015). Contextual Human Trajectory Forecasting within Indoor Environments and Its Applications. (Doctoral Dissertation). University of Houston. Retrieved from http://hdl.handle.net/10657/4880

Chicago Manual of Style (16^th Edition):

Mantini, Pranav 1985-. “Contextual Human Trajectory Forecasting within Indoor Environments and Its Applications.” 2015. Doctoral Dissertation, University of Houston. Accessed January 25, 2021. http://hdl.handle.net/10657/4880.

MLA Handbook (7^th Edition):

Mantini, Pranav 1985-. “Contextual Human Trajectory Forecasting within Indoor Environments and Its Applications.” 2015. Web. 25 Jan 2021.

Vancouver:

Mantini P1. Contextual Human Trajectory Forecasting within Indoor Environments and Its Applications. [Internet] [Doctoral dissertation]. University of Houston; 2015. [cited 2021 Jan 25]. Available from: http://hdl.handle.net/10657/4880.

Council of Science Editors:

Mantini P1. Contextual Human Trajectory Forecasting within Indoor Environments and Its Applications. [Doctoral Dissertation]. University of Houston; 2015. Available from: http://hdl.handle.net/10657/4880

University of Houston

30. Gala, Apurva 1980-. Person Re-Identification in Distributed Wide-Area Surveillance.

Degree: PhD, Computer Vision, 2014, University of Houston

URL: http://hdl.handle.net/10657/5358

► Person re-identification (Re-ID) is a fundamental task in automated video surveillance and has been an area of intense research in the past few years. Given… (more)

Subjects/Keywords: Person re-identification; Open-set Re-ID; Closed-set Re-ID; Short-period Re-ID; Long-period Re-ID; Novelty detection

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Gala, A. 1. (2014). Person Re-Identification in Distributed Wide-Area Surveillance. (Doctoral Dissertation). University of Houston. Retrieved from http://hdl.handle.net/10657/5358

Chicago Manual of Style (16^th Edition):

Gala, Apurva 1980-. “Person Re-Identification in Distributed Wide-Area Surveillance.” 2014. Doctoral Dissertation, University of Houston. Accessed January 25, 2021. http://hdl.handle.net/10657/5358.

MLA Handbook (7^th Edition):

Gala, Apurva 1980-. “Person Re-Identification in Distributed Wide-Area Surveillance.” 2014. Web. 25 Jan 2021.

Vancouver:

Gala A1. Person Re-Identification in Distributed Wide-Area Surveillance. [Internet] [Doctoral dissertation]. University of Houston; 2014. [cited 2021 Jan 25]. Available from: http://hdl.handle.net/10657/5358.

Council of Science Editors:

Gala A1. Person Re-Identification in Distributed Wide-Area Surveillance. [Doctoral Dissertation]. University of Houston; 2014. Available from: http://hdl.handle.net/10657/5358

Open Access Theses and Dissertations