Learning to recognize objects in egocentric activities
Authors:
Top Cited Papers
- 1 June 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3281-3288
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.Keywords
This publication has 17 references indexed in Scilit:
- Figure-ground segmentation improves handled object recognition in egocentric video2010
- Actions in context2009
- Learning realistic human actions from movies2008
- Hierarchical Recognition of Human Activities Interacting with Objects2007
- What, where and who? Classifying events by scene and object recognition2007
- A Statistical Approach to Texture Classification from Single ImagesInternational Journal of Computer Vision, 2005
- Discovering objects and their location in images2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Adaptive background mixture models for real-time tracking2003
- Looking at people: sensing for ubiquitous and wearable computingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000