Learning Motion Categories using both Semantic and Structural Information
- 1 June 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Current approaches to motion category recognition typically focus on either full spatiotemporal volume analysis (holistic approach) or analysis of the content of spatiotemporal interest points (part-based approach). Holistic approaches tend to be more sensitive to noise e.g. geometric variations, while part-based approaches usually ignore structural dependencies between parts. This paper presents a novel generative model, which extends probabilistic latent semantic analysis (pLSA), to capture both semantic (content of parts) and structural (connection between parts) information for motion category recognition. The structural information learnt can also be used to infer the location of motion for the purpose of motion detection. We test our algorithm on challenging datasets involving human actions, facial expressions and hand gestures and show its performance is better than existing unsupervised methods in both tasks of motion localisation and recognition.Keywords
This publication has 14 references indexed in Scilit:
- Behavior Recognition via Sparse Spatio-Temporal FeaturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Unsupervised Learning of Human Action Categories Using Spatial-Temporal WordsPublished by British Machine Vision Association and Society for Pattern Recognition ,2006
- Space-Time Behavior Based CorrelationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Actions as space-time shapesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Pedestrian Detection in Crowded ScenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Discovering objects and their location in imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Detecting irregularities in images and in videoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Recognizing human actions: a local SVM approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Unsupervised learning of human motionIeee Transactions On Pattern Analysis and Machine Intelligence, 2003
- Unsupervised Learning by Probabilistic Latent Semantic AnalysisMachine Learning, 2001