Research map / Video / Action recognition
Actor-Action Semantic Segmentation With Grouping Process Models
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 |
|---|---|---|---|
| add dynamic grouping with the GBH supervoxel hierarchy (ablation) | E^v+E^V segment-level and video-level labeling · A2D, single-label and multiple-label videos | average per-class accuracy | Helped |
| add dynamic grouping with the GBH supervoxel hierarchy (ablation) | E^v+E^V segment-level and video-level labeling · A2D | global pixel accuracy | Hurt |
| use the GBH hierarchy instead of the TSP hierarchy (ablation) | GPM · A2D, all test videos | average per-class accuracy | Helped |
| add GPM to segment-level labeling and video-level recognition | actor-action semantic segmentation · A2D, all test videos | average per-class accuracy: 17% | Helped |
| add GPM to segment-level labeling and video-level recognition | actor-action semantic segmentation · A2D, all test videos | global pixel accuracy: over 10% | Helped |
| use GPM-GBH rather than the intermediate result E^v+E^V (ablation) | actor-action semantic segmentation · A2D, individual actor-action classes | per-class accuracy | Mixed |
Closest papers by meaning
- Weakly Supervised Actor-Action Segmentation via Robust Multi-Task Ranking (CVPR 2017 · similarity 0.89)
- Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation (CVPR 2021 · similarity 0.88)
- Unsupervised Action Segmentation via Fast Learning of Semantically Consistent Actoms (AAAI 2024 · similarity 0.87)
- HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios (NeurIPS 2025 · similarity 0.86)
- FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation (CVPR 2024 · similarity 0.85)
- Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment (CVPR 2024 · similarity 0.84)
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.