Long-term Temporal Convolutions for Action Recognition

15 Apr 2016  ·  Gül Varol, Ivan Laptev, Cordelia Schmid ·

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%).

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Recognition HMDB-51 LTC Average accuracy of 3 splits 64.8 # 63
Action Recognition UCF101 LTC 3-fold Accuracy 91.7 # 63

Methods


No methods listed for this paper. Add relevant methods here