Learning to Recognize Objects in Egocentric Activities

Files
CVPR11.pdf (1.26 MB)
Author(s)
Fathi, Alireza
Ren, Xiaofeng
Advisor(s)
Editor(s)
Associated Organization(s)
Organizational Unit
Organizational Unit
Series
Collections
Research Publications
Supplementary to:
Permanent Link
http://hdl.handle.net/1853/44559
Abstract
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know only the names of the objects which are present within it, and have no other knowledge regarding the appearance or location of objects. The key to our approach is a robust, unsupervised bottom up segmentation method, which exploits the structure of the egocentric domain to partition each frame into hand, object, and background categories. By using Multiple Instance Learning to match object instances across sequences, we discover and localize object occurrences. Object representations are refined through transduction and object-level classifiers are trained. We demonstrate encouraging results in detecting novel object instances using models produced by weakly- supervised learning.
Sponsor
Date
2011-06
Extent
Resource Type
Text
Resource Subtype
Proceedings
Rights Statement
Rights URI