Two-Stream Convolutional Networks for Action Recognition in Videos

Abstract

We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework. Our contribution is three-fold. First, we propose a two-stream ConvNet architecture which incorporates spatial and temporal networks. Second, we demonstrate that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data. Finally, we show that multi-task learning, applied to two different action classification datasets, can be used to increase the amount of training data and improve the performance on both. Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art. It also exceeds by a large margin previous attempts to use deep nets for video classification.

References in corpus (2)

• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice

Cited by in corpus (9)

• Towards Good Practices for Very Deep Two-Stream ConvNets
• Learning Longer Memory in Recurrent Neural Networks
• Evaluating Two-Stream CNN for Video Classification
• Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
• Finding Action Tubes
• Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences
• Temporal Pyramid Pooling Based Convolutional Neural Networks for Action Recognition
• Initialization Strategies of Spatio-Temporal Convolutional Neural Networks
• Long-short Term Motion Feature for Action Classification and Retrieval