TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition

30 Mar 2017Chih-Yao MaMin-Hung ChenZsolt KiraGhassan AlRegib

Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored possible network architectures to further exploit spatiotemporal dynamics within video sequences... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Action Recognition In Videos HMDB-51 TS-LSTM Average accuracy of 3 splits 69 # 16
Action Recognition In Videos UCF101 TS-LSTM 3-fold Accuracy 94.1 # 15