Poselet Key-Framing: A Model for Human Activity Recognition
- 1 June 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2013 IEEE Conference on Computer Vision and Pattern Recognition
- p. 2650-2657
- https://doi.org/10.1109/cvpr.2013.342
Abstract
In this paper, we develop a new model for recognizing human actions. An action is modeled as a very sparse sequence of temporally local discriminative key frames - collections of partial key-poses of the actor(s), depicting key states in the action sequence. We cast the learning of key frames in a max-margin discriminative framework, where we treat key frames as latent variables. This allows us to (jointly) learn a set of most discriminative key frames while also learning the local temporal context between them. Key frames are encoded using a spatially-localizable pose let-like representation with HoG and BoW components learned from weak annotations, we rely on structured SVM formulation to align our components and mine for hard negatives to boost localization performance. This results in a model that supports spatio-temporal localization and is insensitive to dropped frames or partial observations. We show classification performance that is competitive with the state of the art on the benchmark UT-Interaction dataset and illustrate that our model outperforms prior methods in an on-line streaming setting.Keywords
This publication has 27 references indexed in Scilit:
- A discriminative key pose sequence model for recognizing human interactionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Recognizing human actions by attributesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Learning hierarchical poselets for human parsingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Recognizing human actions from still images with latent posesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Efficient Subwindow Search: A Branch and Bound Framework for Object LocalizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Pose primitive based human action recognition in videos or still imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Information Theoretic Key Frame Selection for Action RecognitionPublished by British Machine Vision Association and Society for Pattern Recognition ,2008
- Searching Video for Complex Activities with Finite State ModelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- On Space-Time Interest PointsInternational Journal of Computer Vision, 2005
- Activation in Human MT/MST by Static Images with Implied MotionJournal of Cognitive Neuroscience, 2000