Papers › Temporal Relational Modeling with Self-Supervision for Action Segmentation
Temporal Relational Modeling with Self-Supervision for Action Segmentation
Dong Wang, Di Hu, Xingjian Li, Dejing Dou
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Segmentation | 50 Salads | DTGRM | Acc | 80 | #25 of 28 | Archive leaderboard | report |
| Action Segmentation | 50 Salads | DTGRM | Edit | 72 | #25 of 28 | Archive leaderboard | report |
| Action Segmentation | 50 Salads | DTGRM | F1@10% | 79.1 | #25 of 28 | Archive leaderboard | report |
| Action Segmentation | 50 Salads | DTGRM | F1@25% | 75.9 | #25 of 28 | Archive leaderboard | report |
| Action Segmentation | 50 Salads | DTGRM | F1@50% | 66.1 | #25 of 28 | Archive leaderboard | report |
| Action Segmentation | Breakfast | DTGRM | Acc | 68.3 | #26 of 37 | Archive leaderboard | report |
| Action Segmentation | Breakfast | DTGRM | Average F1 | 59.1 | #26 of 37 | Archive leaderboard | report |
| Action Segmentation | Breakfast | DTGRM | Edit | 68.9 | #26 of 37 | Archive leaderboard | report |
| Action Segmentation | Breakfast | DTGRM | F1@10% | 68.7 | #26 of 37 | Archive leaderboard | report |
| Action Segmentation | Breakfast | DTGRM | F1@25% | 61.9 | #26 of 37 | Archive leaderboard | report |
| Action Segmentation | Breakfast | DTGRM | F1@50% | 46.6 | #26 of 37 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections