pith. sign in

arxiv: 1604.04494 · v2 · pith:LNFOWQOHnew · submitted 2016-04-15 · 💻 cs.CV

Long-term Temporal Convolutions for Action Recognition

classification 💻 cs.CV
keywords actionrepresentationstemporalrecognitionvideoactionsconvolutionsdemonstrate
0
0 comments X
read the original 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%).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.