Discovering Primitive Action Categories by Leveraging Relevant Visual Context

October 2008

Discovering Primitive Action Categories by Leveraging Relevant Visual Context

Authors:

Kris M. Kitani, Takahiro Okabe, Yoichi Sato, and Akihiro Sugimoto

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.
@workshop{Kitani-2008-109831,
author = {Kris M. Kitani And Takahiro Okabe And Yoichi Sato And Akihiro Sugimoto},
title = {Discovering Primitive Action Categories by Leveraging Relevant Visual Context},
booktitle = {Proceedings of ECCV '08 8th International Workshop on Visual Surveillance (VS '08)},
year = {2008},
month = {October},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.