Dense trajectories and motion boundary descriptors for action recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2012

Dense trajectories and motion boundary descriptors for action recognition

Alexander Kläser
  • Function : Author
  • PersonId : 865348
Cordelia Schmid
  • Function : Author
  • PersonId : 831154
Cheng-Lin Liu
  • Function : Author
  • PersonId : 836103


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.
Fichier principal
Vignette du fichier
RR-8050.pdf (6.37 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00725627 , version 1 (27-08-2012)
hal-00725627 , version 2 (25-01-2013)


  • HAL Id : hal-00725627 , version 2


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⟩
2245 View
12293 Download


Gmail Facebook X LinkedIn More