Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

2 Aug 2016  ·  Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, Luc van Gool ·

Deep 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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multimodal Activity Recognition EV-Action TSN (RGB) Accuracy 73.6 # 3
Action Recognition HMDB-51 Temporal Segment Networks Average accuracy of 3 splits 69.4 # 52
Action Recognition UCF101 Temporal Segment Networks 3-fold Accuracy 94.2 # 49

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Action Classification Kinetics-400 TSN Vid acc@1 73.9 # 103
Vid acc@5 91.1 # 78

Methods


No methods listed for this paper. Add relevant methods here