Better exploiting motion for better action recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Better exploiting motion for better action recognition

Abstract

Several recent works on action recognition have attested the importance of explicitly integrating motion characteristics in the video description. This paper establishes that adequately decomposing visual motion into dominant and residual motions, both in the extraction of the space-time trajectories and for the computation of descriptors, significantly improves action recognition algorithms. Then, we design a new motion descriptor, the DCS descriptor, based on differential motion scalar quantities, divergence, curl and shear features. It captures additional information on the local motion patterns enhancing results. Finally, applying the recent VLAD coding technique proposed in image retrieval provides a substantial improvement for action recognition. Our three contributions are complementary and lead to outperform all reported results by a significant margin on three challenging datasets, namely Hollywood~2, HMDB51 and Olympic Sports.
Fichier principal
Vignette du fichier
jain_motion.pdf (3.44 Mo) Télécharger le fichier
Vignette du fichier
jain_motion.png (79.77 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Loading...

Dates and versions

hal-00813014 , version 1 (14-04-2013)

Identifiers

  • HAL Id : hal-00813014 , version 1

Cite

Mihir Jain, Hervé Jégou, Patrick Bouthemy. Better exploiting motion for better action recognition. CVPR - International Conference on Computer Vision and Pattern Recognition, Jun 2013, Portland, United States. ⟨hal-00813014⟩
649 View
1239 Download

Share

Gmail Facebook X LinkedIn More