Research map / Video / Action recognition
Weakly Supervised Actor-Action Segmentation via Robust Multi-Task Ranking
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use robust multi-task ranking with shared actor and action features and outlier-task handling | Weakly supervised actor-action segmentation · A2D | overall pixel accuracy (Actor-Action): 70.4 -> 81.7 | Helped |
| Add coarse actor and action labels alongside fine-grained actor-action labels (ablation) | Ours · A2D | overall pixel accuracy: 72.6% -> 81.7% | Helped |
| Use fine-level rather than coarser-level GBH supervoxels (ablation) | Ours · A2D | overall pixel accuracy | Helped |
Closest papers by meaning
- Learning a Weakly-Supervised Video Actor-Action Segmentation Model With a Wise Selection (CVPR 2020 · similarity 0.91)
- Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints (CVPR 2018 · similarity 0.91)
- Understanding Multi-Task Activities from Single-Task Videos (CVPR 2025 · similarity 0.87)
- Unsupervised Action Segmentation via Fast Learning of Semantically Consistent Actoms (AAAI 2024 · similarity 0.87)
- Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment (CVPR 2024 · similarity 0.86)
- FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.