Skip to Main content Skip to Navigation
New interface
Journal articles

Long-term Temporal Convolutions for Action Recognition

Gül Varol 1, 2 Ivan Laptev 1 Cordelia Schmid 2 
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique - ENS Paris, Inria de Paris
2 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : Typical human actions last several seconds and exhibit characteristic spatio-temporal structure. Recent methods attempt to capture this structure and learn action representations with convolutional neural networks. Such representations, however, are typically learned at the level of a few video frames failing to model actions at their full temporal extent. In this work we learn video representations using neural networks with long-term temporal convolutions (LTC). We demonstrate that LTC-CNN models with increased temporal extents improve the accuracy of action recognition. We also study the impact of different low-level representations, such as raw values of video pixels and optical flow vector fields and demonstrate the importance of high-quality optical flow estimation for learning accurate action models. We report state-of-the-art results on two challenging benchmarks for human action recognition UCF101 (92.7%) and HMDB51 (67.2%).
Document type :
Journal articles
Complete list of metadata

Cited literature [33 references]  Display  Hide  Download
Contributor : Gul Varol Connect in order to contact the contributor
Submitted on : Friday, June 2, 2017 - 2:04:32 PM
Last modification on : Friday, July 8, 2022 - 10:06:50 AM


Files produced by the author(s)




Gül Varol, Ivan Laptev, Cordelia Schmid. Long-term Temporal Convolutions for Action Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40 (6), pp.1510-1517. ⟨10.1109/TPAMI.2017.2712608⟩. ⟨hal-01241518v3⟩



Record views


Files downloads