PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Exemplar-based action recognition in video
Geert Willems, Jan Hendrik Becker, Tinne Tuytelaars and Luc Van Gool
In: BMVC 2009, 7-10 September 2009, London, UK.

Abstract

In this work, we present a method for action localization and recognition using an exemplar-based approach. It starts from local dense yet scale-invariant spatio-temporal features. The most discriminative visual words are selected and used to cast bounding box hypotheses, which are then verified and further grouped into the final detections. To the best of our knowledge, we are the first to extend the exemplar-based approach using local features into the spatio-temporal domain. This allows us to avoid the problems that typically plague sliding window-based approaches - in particular the exhaustive search over spatial coordinates, time, and spatial as well as temporal scales. We report state-ofthe- art results on challenging datasets, extracted from real movies, for both classification and localization.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:6586
Deposited By:Tinne Tuytelaars
Deposited On:08 March 2010