Dense trajectories and motion boundary descriptors for action recognition

Heng Wang 1, * 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, INPG - Institut National Polytechnique de Grenoble
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 state-of-the-art optical flow algorithm enables a robust and efficient extraction of the 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 eight datasets, namely KTH, YouTube, Hollywood2, UCF sports, IXMAS, UIUC, Olympic Sports and UCF50. On all datasets our approach outperforms current state-of-the-art results.
Complete list of metadatas

Cited literature [65 references]  Display  Hide  Download

https://hal.inria.fr/hal-00725627
Contributor : Heng Wang <>
Submitted on : Friday, January 25, 2013 - 6:25:42 PM
Last modification on : Thursday, April 11, 2019 - 2:34:03 PM
Long-term archiving on : Saturday, April 1, 2017 - 10:47:51 AM

Files

RR-8050.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00725627, version 2

Collections

Citation

Heng Wang, Alexander Kläser, Cordelia Schmid, Cheng-Lin Liu. Dense trajectories and motion boundary descriptors for action recognition. [Research Report] RR-8050, INRIA. 2012. ⟨hal-00725627v2⟩

Share

Metrics

Record views

2610

Files downloads

15667