Skip to Main content Skip to Navigation
New interface
Conference papers

Focused Attention for Action Recognition

Vladyslav Sydorov 1 Karteek Alahari 1 Cordelia Schmid 1 
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : Current state-of-the art approaches to action recognition emphasize learning ConvNets on large amounts of training data, using 3D convolutions to process the temporal dimension. This approach is expensive in terms of memory usage and constitutes a major performance bottleneck of existing approaches. Further, video input data points typically include irrelevant information, along with useful features, which limits the level of detail that networks can process, regardless of the quality of the original video. Hence, models that can focus computational resources on relevant training signal are desirable.To address this problem, we rely on network-specific saliency outputs to drive an attention model that provides tighter crops around relevant video regions. We experimentally validate this approach and show how this strategy improves performance for the action recognition task.
Document type :
Conference papers
Complete list of metadata

Cited literature [43 references]  Display  Hide  Download
Contributor : Vladyslav Sydorov Connect in order to contact the contributor
Submitted on : Thursday, September 19, 2019 - 4:29:49 PM
Last modification on : Wednesday, May 4, 2022 - 12:18:03 PM
Long-term archiving on: : Saturday, February 8, 2020 - 9:44:27 PM


Files produced by the author(s)


  • HAL Id : hal-02292339, version 1



Vladyslav Sydorov, Karteek Alahari, Cordelia Schmid. Focused Attention for Action Recognition. BMVC 2019 - British Machine Vision Conference, Sep 2019, Cardiff, United Kingdom. pp.1-13. ⟨hal-02292339⟩



Record views


Files downloads