Temporal Relational Modeling with Self-Supervision for Action Segmentation
This work provides an incremental improvement in action segmentation for researchers and practitioners working with long video sequences.
This paper addresses the challenge of applying Graph Convolution Networks (GCNs) to long video sequences for action segmentation by introducing the Dilated Temporal Graph Reasoning Module (DTGRM). The DTGRM models temporal relations and dependencies between video frames at various time spans using multi-level dilated temporal graphs, and an auxiliary self-supervised task enhances its temporal reasoning ability. The model achieves state-of-the-art performance on the 50Salads, GTEA, and Breakfast datasets.
Temporal relational modeling in video is essential for human action understanding, such as action recognition and action segmentation. Although Graph Convolution Networks (GCNs) have shown promising advantages in relation reasoning on many tasks, it is still a challenge to apply graph convolution networks on long video sequences effectively. The main reason is that large number of nodes (i.e., video frames) makes GCNs hard to capture and model temporal relations in videos. To tackle this problem, in this paper, we introduce an effective GCN module, Dilated Temporal Graph Reasoning Module (DTGRM), designed to model temporal relations and dependencies between video frames at various time spans. In particular, we capture and model temporal relations via constructing multi-level dilated temporal graphs where the nodes represent frames from different moments in video. Moreover, to enhance temporal reasoning ability of the proposed model, an auxiliary self-supervised task is proposed to encourage the dilated temporal graph reasoning module to find and correct wrong temporal relations in videos. Our DTGRM model outperforms state-of-the-art action segmentation models on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset. The code is available at https://github.com/redwang/DTGRM.