Convolutional Two-Stream Network Fusion for Video Action Recognition
This work addresses the challenge of efficiently combining spatio-temporal data for video action recognition, which is incremental as it builds on existing ConvNet approaches.
The paper tackles the problem of fusing appearance and motion information in video action recognition by studying spatial and temporal fusion methods within convolutional neural networks, resulting in a new architecture that achieves state-of-the-art performance on standard benchmarks.
Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet towers both spatially and temporally in order to best take advantage of this spatio-temporal information. We make the following findings: (i) that rather than fusing at the softmax layer, a spatial and temporal network can be fused at a convolution layer without loss of performance, but with a substantial saving in parameters; (ii) that it is better to fuse such networks spatially at the last convolutional layer than earlier, and that additionally fusing at the class prediction layer can boost accuracy; finally (iii) that pooling of abstract convolutional features over spatiotemporal neighbourhoods further boosts performance. Based on these studies we propose a new ConvNet architecture for spatiotemporal fusion of video snippets, and evaluate its performance on standard benchmarks where this architecture achieves state-of-the-art results.