Action bank: A high-level representation of activity in video
Top Cited Papers
- 1 June 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2012 IEEE Conference on Computer Vision and Pattern Recognition
- p. 1234-1241
- https://doi.org/10.1109/cvpr.2012.6247806
Abstract
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 recent object bank approach to image representation, we present Action Bank, a new high-level representation of video. Action bank is comprised of many individual action detectors sampled broadly in semantic space as well as viewpoint space. Our representation is constructed to be semantically rich and even when paired with simple linear SVM classifiers is capable of highly discriminative performance. We have tested action bank on four major activity recognition benchmarks. In all cases, our performance is better than the state of the art, namely 98.2% on KTH (better by 3.3%), 95.0% on UCF Sports (better by 3.7%), 57.9% on UCF50 (baseline is 47.9%), and 26.9% on HMDB51 (baseline is 23.2%). Furthermore, when we analyze the classifiers, we find strong transfer of semantics from the constituent action detectors to the bank classifier.Keywords
This publication has 31 references indexed in Scilit:
- HMDB: A large video database for human motion recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Action recognition by dense trajectoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Secrets of optical flow estimation and their principlesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Learning a hierarchy of discriminative space-time neighborhood features for human action recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Local Trinary Patterns for human action recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- More generality in efficient multiple kernel learningPublished by Association for Computing Machinery (ACM) ,2009
- Learning realistic human actions from moviesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- A Spatio-Temporal Descriptor Based on 3D-GradientsPublished by British Machine Vision Association and Society for Pattern Recognition ,2008
- On Space-Time Interest PointsInternational Journal of Computer Vision, 2005
- Recognizing human actions: a local SVM approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004