Sciweavers

ACL
2012
12 years 1 months ago
Temporally Anchored Relation Extraction
Although much work on relation extraction has aimed at obtaining static facts, many of the target relations are actually fluents, as their validity is naturally anchored to a cer...
Guillermo Garrido, Anselmo Peñas, Bernardo ...
CVPR
2012
IEEE
12 years 1 months ago
Action bank: A high-level representation of activity in video
Activity recognition in video is dominated by low- and mid-level features, and while demonstrably capable, by nature, these features carry little semantic meaning. Inspired by the...
Sreemanananth Sadanand, Jason J. Corso
NIPS
2004
14 years 25 days ago
A Three Tiered Approach for Articulated Object Action Modeling and Recognition
Visual action recognition is an important problem in computer vision. In this paper, we propose a new method to probabilistically model and recognize actions of articulated object...
Le Lu, Gregory D. Hager, Laurent Younes