Cost-Sensitive Top-Down/Bottom-Up Inference for Multiscale Activity Recognition
Authors:
- 1 January 2012
- book chapter
- Published by Springer Nature
- p. 187-200
Abstract
No abstract availableKeywords
This publication has 15 references indexed in Scilit:
- Sum-product networks for modeling activities with stochastic structure2012
- Unsupervised learning of event AND-OR grammar and semantics from video2011
- Action recognition using context and appearance distribution features2011
- Learning context for collective activity recognition2011
- Stochastic Representation and Recognition of High-Level Group ActivitiesInternational Journal of Computer Vision, 2010
- A Numerical Study of the Bottom-Up and Top-Down Inference Processes in And-Or GraphsInternational Journal of Computer Vision, 2010
- Learning deformable action templates from cluttered videos2009
- Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos2009
- Efficient Visual Search for Objects in VideosProceedings of the IEEE, 2008
- A Stochastic Grammar of ImagesFoundations and Trends in Computer Graphics and Vision, 2007