Skip to Main content Skip to Navigation
Conference papers

Actlets: A novel local representation for human action recognition in video

Muhammad M. Ullah 1 Ivan Laptev 1 
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique - ENS Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : This paper addresses the problem of human action recognition in realistic videos. We follow the recently successful local approaches and represent videos by means of local motion descriptors. To overcome the huge variability of human actions in motion and appearance, we propose a supervised approach to learn local motion descriptors - actlets - from a large pool of annotated video data. The main motivation behind our method is to construct action-characteristic representations of body joints undergoing specific motion patterns while learning invariance with respect to changes in camera views, lighting, human clothing, and other factors. We avoid the prohibitive cost of manual supervision and show how to learn actlets automatically from synthetic videos of avatars driven by the motion-capture data. We evaluate our method and show its significant improvement as well as its complementarity to existing techniques on the challenging UCF-sports and YouTube-actions datasets.
Document type :
Conference papers
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download
Contributor : Suha Kwak Connect in order to contact the contributor
Submitted on : Thursday, September 11, 2014 - 6:09:09 PM
Last modification on : Thursday, March 17, 2022 - 10:08:39 AM
Long-term archiving on: : Friday, December 12, 2014 - 10:57:24 AM


Files produced by the author(s)




Muhammad M. Ullah, Ivan Laptev. Actlets: A novel local representation for human action recognition in video. ICIP 2012 - International Conference on Image Processing, Sep 2012, Orlando, Florida, United States. pp.777 - 780, ⟨10.1109/ICIP.2012.6466975⟩. ⟨hal-01063332⟩



Record views


Files downloads