Skip to Main content Skip to Navigation
New interface
Journal articles

Dense trajectories and motion boundary descriptors for action recognition

Heng Wang 1, 2, * Alexander Kläser 1, * Cordelia Schmid 1, * Cheng-Lin Liu 2, * 
* Corresponding author
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : This paper introduces a video representation based on dense trajectories and motion boundary descriptors. Trajectories capture the local motion information of the video. A dense representation guarantees a good coverage of foreground motion as well as of the surrounding context. A stateof- the-art optical flow algorithm enables a robust and efficient extraction of dense trajectories. As descriptors we extract features aligned with the trajectories to characterize shape (point coordinates), appearance (histograms of oriented gradients) and motion (histograms of optical flow). Additionally, we introduce a descriptor based on motion boundary histograms (MBH) which rely on differential optical flow. The MBH descriptor shows to consistently outperform other state-of-the-art descriptors, in particular on real-world videos that contain a significant amount of camera motion. We evaluate our video representation in the context of action classification on nine datasets, namely KTH, YouTube, Hollywood2, UCF sports, IXMAS, UIUC, Olympic Sports, UCF50 and HMDB51. On all datasets our approach outperforms current state-of-the-art results.
Document type :
Journal articles
Complete list of metadata
Contributor : Heng Wang Connect in order to contact the contributor
Submitted on : Thursday, March 21, 2013 - 2:35:29 PM
Last modification on : Thursday, January 20, 2022 - 5:28:04 PM
Long-term archiving on: : Monday, June 24, 2013 - 11:50:37 AM


Files produced by the author(s)




Heng Wang, Alexander Kläser, Cordelia Schmid, Cheng-Lin Liu. Dense trajectories and motion boundary descriptors for action recognition. International Journal of Computer Vision, 2013, 103 (1), pp.60-79. ⟨10.1007/s11263-012-0594-8⟩. ⟨hal-00803241⟩



Record views


Files downloads