Skip to Main content Skip to Navigation
Conference papers

Discovering Primitive Action Categories by Leveraging Relevant Visual Context

Abstract : Under the bag-of-features framework we aim to learn primitive action categories from video without supervision by leveraging relevant visual context in addition to motion features. We define visual context as the appearance of the entire scene including the actor, related objects and relevant background features. To leverage visual context along with motion features, we learn a bi-modal latent variable model to discover action categories without supervision. Our experiments show that the combination of relevant visual context and motion features improves the performance of action discovery. Furthermore, we show that our method is able to leverage relevant visual features for action discovery despite the presence of irrelevant background objects.
Document type :
Conference papers
Complete list of metadata

Cited literature [30 references]  Display  Hide  Download
Contributor : Peter Sturm Connect in order to contact the contributor
Submitted on : Tuesday, September 30, 2008 - 11:28:59 AM
Last modification on : Monday, May 17, 2021 - 12:00:04 PM
Long-term archiving on: : Friday, June 4, 2010 - 12:00:04 PM


Files produced by the author(s)


  • HAL Id : inria-00325777, version 1



Kris M. Kitani, Takahiro Okabe, Yoichi Sato, Akihiro Sugimoto. Discovering Primitive Action Categories by Leveraging Relevant Visual Context. The Eighth International Workshop on Visual Surveillance - VS2008, Graeme Jones and Tieniu Tan and Steve Maybank and Dimitrios Makris, Oct 2008, Marseille, France. ⟨inria-00325777⟩



Record views


Files downloads