Full Record

New Search | Similar Records

Title Embodied learning for visual recognition
Publication Date
Date Accessioned
Degree PhD
Discipline/Department Electrical and Computer Engineering
Degree Level doctoral
University/Publisher University of Texas – Austin
Abstract The field of visual recognition in recent years has come to rely on large expensively curated and manually labeled "bags of disembodied images". In the wake of this, my focus has been on understanding and exploiting alternate "free" sources of supervision available to visual learning agents that are situated within real environments. For example, even simply moving from orderless image collections to continuous visual observations offers opportunities to understand the dynamics and other physical properties of the visual world. Further, embodied agents may have the abilities to move around their environment and/or effect changes within it, in which case these abilities offer new means to acquire useful supervision. In this dissertation, I present my work along this and related directions.
Subjects/Keywords Computer vision; Unsupervised learning; Embodied learning
Contributors Grauman, Kristen Lorraine, 1979- (advisor); Efros, Alexei (committee member); Ghosh, Joydeep (committee member); Niekum, Scott (committee member); Thomaz, Andrea (committee member)
Language en
Country of Publication us
Record ID handle:2152/63489
Repository texas
Date Retrieved
Date Indexed 2019-09-12
Grantor The University of Texas at Austin
Issued Date 2017-08-10 00:00:00
Note [department] Electrical and Computer Engineering;

Sample Images