A discriminative key pose sequence model for recognizing human interactions
- 1 November 2011
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1729-1736
- https://doi.org/10.1109/iccvw.2011.6130458
Abstract
In this paper we develop a model for recognizing human interactions - activity recognition with multiple actors. An activity is modeled with a sequence of key poses, important atomic-level actions performed by the actors. Spatial arrangements between the actors are included in the model, as is a strict temporal ordering of the key poses. An exemplar representation is used to model the variability in the instantiation of key poses. Quantitative results that form a new state-of-the-art on the benchmark UT-Interaction dataset are presented, along with results on a subset of the TRECVID dataset.Keywords
This publication has 18 references indexed in Scilit:
- Human Action Segmentation and Recognition Using Discriminative Semi-Markov ModelsInternational Journal of Computer Vision, 2010
- A Hough transform-based voting framework for action recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Real-time Action Recognition by Spatiotemporal Semantic and Structural ForestsPublished by British Machine Vision Association and Society for Pattern Recognition ,2010
- Spatio-temporal relationship match: Video structure comparison for recognition of complex human activitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Human Action Recognition by Semilatent Topic ModelsIeee Transactions On Pattern Analysis and Machine Intelligence, 2009
- Action recognition using exemplar-based embeddingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Incremental Learning for Robust Visual TrackingInternational Journal of Computer Vision, 2007
- Evaluation campaigns and TRECVidPublished by Association for Computing Machinery (ACM) ,2006
- Beyond Tracking: Modelling Activity and Understanding BehaviourInternational Journal of Computer Vision, 2006
- Recognizing human action in time-sequential images using hidden Markov modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003