Year: 2017
Type: article
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%).
Authors: Gul Varol, Ivan Laptev, Cordelia Schmid
Institutions: Centre National de la Recherche Scientifique, Institut national de recherche en sciences et technologies du numérique, École Normale Supérieure - PSL, Département d'Informatique, THOTH: Apprentissage de modèles visuels à partir de données massives, WILLOW: Vision par ordinateur incarnée, Laboratoire Jean Kuntzmann
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: European Research Council
OpenAlex ID: W2235034809