Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
Refereed conference paper presented and published in conference proceedings

Times Cited
Web of Science411WOS source URL (as at 05/07/2020) Click here for the latest count
Altmetrics Information

Other information
AbstractDeep convolutional networks have achieved great success for visual recognition in still images. However, for action recognition in videos, the advantage over traditional methods is not so evident. This paper aims to discover the principles to design effective ConvNet architectures for action recognition in videos and learn these models given limited training samples. Our first contribution is temporal segment network (TSN), a novel framework for video-based action recognition. which is based on the idea of long-range temporal structure modeling. It combines a sparse temporal sampling strategy and video-level supervision to enable efficient and effective learning using the whole action video. The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network. Our approach obtains the state-the-of-art performance on the datasets of HMDB51 (69.4%) and UCF101 (94.2%). We also visualize the learned ConvNet models, which qualitatively demonstrates the effectiveness of temporal segment network and the proposed good practices
All Author(s) ListWang LM, Xiong YJ, Wang Z, Qiao Y, Lin DH, Tang XO, Van Gool L
Name of Conference14th European Conference on Computer Vision (ECCV)
Start Date of Conference08/10/2016
End Date of Conference16/10/2016
Place of ConferenceAmsterdam
Country/Region of ConferenceNetherlands
Volume Number9912
Pages20 - 36
LanguagesEnglish-United Kingdom
KeywordsAction recognition; ConvNets; Good practices; Temporal segment networks
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence; Computer Science, Theory & Methods; Imaging Science & Photographic Technology

Last updated on 2020-06-07 at 02:21