Search For:

Displaying 1-4 out of 4 total
Learning to recognize objects in egocentric activities
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By A. Fathi, Xiaofeng Ren,J. M. Rehg
Issue Date:June 2011
pp. 3281-3288
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 kno...
Learning sparse covariance patterns for natural scenes
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Liwei Wang, Yin Li, Jiaya Jia, Jian Sun,D. Wipf,J. M. Rehg
Issue Date:June 2012
pp. 2767-2774
For scene classification, patch-level linear features do not always work as well as handcrafted features. In this paper, we present a new model to greatly improve the usefulness of linear features in classification by introducing co-variance patterns. We a...
Social interactions: A first-person perspective
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By A. Fathi,J. K. Hodgins,J. M. Rehg
Issue Date:June 2012
pp. 1226-1233
This paper presents a method for the detection and recognition of social interactions in a day-long first-person video of u social event, like a trip to an amusement park. The location and orientation of faces are estimated and used to compute the line of ...
Video-Based Crowd Synthesis
Found in: IEEE Transactions on Visualization and Computer Graphics
By M. Flagg,J. M. Rehg
Issue Date:November 2013
pp. 1935-1947
As a controllable medium, video-realistic crowds are important for creating the illusion of a populated reality in special effects, games, and architectural visualization. While recent progress in simulation and motion captured-based techniques for crowd s...