Research map / Video / Action recognition
Refining Action Segmentation With Hierarchical Video Representations
Hyemin Ahn, Dongheui Lee
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 HASR refinement | MS-TCN · 50Salads | Edit score: 70.4 -> 77.4 | Improved |
| add HASR refinement | ASRF · 50Salads | Edit score: 79.9 -> 81.0 | Improved |
| add HASR refinement | SSTDA · 50Salads | Edit score: 74.9 -> 77.3 | Improved |
| add HASR refinement | GRU · Breakfast | Edit score: 32.3 -> 61.2 | Improved |
| add HASR refinement | MS-TCN · Breakfast | Edit score: 66.2 -> 70.8 | Improved |
| add HASR refinement | SSTDA · Breakfast | Edit score: 70.2 -> 70.0 | No clear effect |
| add HASR refinement | SSTDA · GTEA | Edit score: 87.9 -> 87.5 | No clear effect |
| add HASR refinement | MS-TCN · GTEA | Frame accuracy: 78.3 -> 77.4 | Hurt |
| refine backbone with HASR trained on other backbones (unseen) | GRU · Breakfast | Edit score: 32.3 -> 53.0 | Improved |
| add segment-level representation (ablation) | HASR · 50Salads | Edit score: 72.3 -> 77.4 | Improved |
| add video-level representation (ablation) | HASR · 50Salads | Edit score: 74.9 -> 77.4 | Improved |
| use sample-based residual blocks instead of GRU for video-level encoder (ablation) | HASR · 50Salads | Edit score: 76.7 -> 77.4 | Improved |
Closest papers by meaning
- Video Action Segmentation via Contextually Refined Temporal Keypoints (ICCV 2023 · similarity 0.89)
- Unsupervised Action Segmentation via Fast Learning of Semantically Consistent Actoms (AAAI 2024 · similarity 0.89)
- Leveraging Action Affinity and Continuity for Semi-Supervised Temporal Action Segmentation (ECCV 2022 · similarity 0.89)
- Hierarchical Vector Quantization for Unsupervised Action Segmentation (AAAI 2025 · similarity 0.88)
- FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation (CVPR 2024 · similarity 0.88)
- OnlineTAS: An Online Baseline for Temporal Action Segmentation (NeurIPS 2024 · similarity 0.87)
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.
