Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection
Preprint
Abstract
This paper proposes a segregated temporal assembly recurrent (STAR) network for weakly-supervised multiple action detection. The model learns from untrimmed videos with only supervision of video-level labels and makes prediction of intervals of multiple actions. Specifically, we first assemble video clips according to class labels by an attention mechanism that learns class-variable attention weights and thus helps the noise relieving from background or other actions. Secondly, we build temporal relationship between actions by feeding the assembled features into an enhanced recurrent neural network. Finally, we transform the output of recurrent neural network into the corresponding action distribution. In order to generate more precise temporal proposals, we design a score term called segregated temporal gradient-weighted class activation mapping (ST-GradCAM) fused with attention weights. Experiments on THUMOS'14 and ActivityNet1.3 datasets show that our approach outperforms the state-of-the-art weakly-supervised method, and performs at par with the fully-supervised counterparts.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization2018
- Multi-evidence Filtering and Fusion for Multi-label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning2018
- Learning Latent Super-Events to Detect Multiple Activities in Videos2018
- R-C3D: Region Convolutional 3D Network for Temporal Activity Detection2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Cascaded Boundary Regression for Temporal Action Detection2017