Papers › ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources
ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources
Beatrice van Amsterdam, Abdolrahim Kadkhodamohammadi, Imanol Luengo, Danail Stoyanov
Most state-of-the-art methods for action segmentation are based on single input modalities or naive fusion of multiple data sources. However, effective fusion of complementary information can potentially strengthen segmentation models and make them more robust to sensor noise and more accurate with smaller training datasets. In order to improve multimodal representation learning for action segmentation, we propose to disentangle hidden features of a multi-stream segmentation model into modality-shared components, containing common information across data sources, and private components; we then use an attention bottleneck to capture long-range temporal dependencies in the data while preserving disentanglement in consecutive processing layers. Evaluation on 50salads, Breakfast and RARP45 datasets shows that our multimodal approach outperforms different data fusion baselines on both multiview and multimodal data sources, obtaining competitive or better results compared with the state-of-the-art. Our model is also more robust to additive sensor noise and can achieve performance on par with strong video baselines even with less training data.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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 | Br-Prompt+ASPnet (RGB, flow, accelerometer) | Acc | 91.4 | #1 of 28 | Archive leaderboard | report |
| Action Segmentation | 50 Salads | Br-Prompt+ASPnet (RGB, flow, accelerometer) | Edit | 87.5 | #1 of 28 | Archive leaderboard | report |
| Action Segmentation | 50 Salads | Br-Prompt+ASPnet (RGB, flow, accelerometer) | F1@10% | 92.7 | #1 of 28 | Archive leaderboard | report |
| Action Segmentation | 50 Salads | Br-Prompt+ASPnet (RGB, flow, accelerometer) | F1@25% | 91.6 | #1 of 28 | Archive leaderboard | report |
| Action Segmentation | 50 Salads | Br-Prompt+ASPnet (RGB, flow, accelerometer) | F1@50% | 88.5 | #1 of 28 | Archive leaderboard | report |
| Action Segmentation | Breakfast | ASPnet | Acc | 75.9 | #9 of 37 | Archive leaderboard | report |
| Action Segmentation | Breakfast | ASPnet | Average F1 | 70.6 | #9 of 37 | Archive leaderboard | report |
| Action Segmentation | Breakfast | ASPnet | Edit | 76.3 | #9 of 37 | Archive leaderboard | report |
| Action Segmentation | Breakfast | ASPnet | F1@10% | 78.1 | #9 of 37 | Archive leaderboard | report |
| Action Segmentation | Breakfast | ASPnet | F1@25% | 72.9 | #9 of 37 | Archive leaderboard | report |
| Action Segmentation | Breakfast | ASPnet | F1@50% | 60.8 | #9 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.
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