Research map / Video / Action recognition
Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos
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 online DP inference instead of greedy sliding-window prediction | Online action segmentation · Breakfast | IoU: 7.4 -> 22.4 | Helped |
| Use online DP inference instead of greedy sliding-window prediction | Online action segmentation · IKEA ASM | IoU: 30.9 -> 33.3 | Helped |
| Add multi-view training and OODL to online DP | DP_on · Breakfast | IoU: 22.4 -> 25.0 | Helped |
| Add multi-view training and OODL to online DP | DP_on · IKEA ASM | IoU: 33.3 -> 36.8 | Helped |
| Remove OODL (ablation) | DP_on + OODL · Breakfast | IoU: 22.4 -> 23.4 | Hurt |
| Add OODL (ablation) | DP_on · IKEA ASM | acc: 55.3 -> 55.3 | No clear effect |
| Add OODL (ablation) | DP_on · Breakfast | IoD: 46.9 -> 48.0 | Helped |
| Add OODL (ablation) | DP_on · IKEA ASM | IoD: 44.1 -> 45.5 | Helped |
| Remove the half-Poisson Γ duration factor (ablation) | DP_on · Breakfast | IoU: 22.4 -> 21.4 | Hurt |
| Remove the half-Poisson Γ duration factor (ablation) | DP_on · IKEA ASM | IoU: 33.3 -> 30.0 | Hurt |
| Add multi-view supervision (ablation) | CDFL offline segmentation · Breakfast | IoU: 31.0 -> 33.3 | Helped |
| Add multi-view supervision (ablation) | CDFL offline segmentation · IKEA ASM | IoU: 39.5 -> 41.7 | Helped |
Closest papers by meaning
- Semi-Weakly-Supervised Learning of Complex Actions From Instructional Task Videos (CVPR 2022 · similarity 0.90)
- OnlineTAS: An Online Baseline for Temporal Action Segmentation (NeurIPS 2024 · similarity 0.88)
- Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis (AAAI 2024 · similarity 0.88)
- Detours for Navigating Instructional Videos (CVPR 2024 · similarity 0.87)
- Unsupervised Action Segmentation via Fast Learning of Semantically Consistent Actoms (AAAI 2024 · similarity 0.86)
- Hierarchical Vector Quantization for Unsupervised Action Segmentation (AAAI 2025 · 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.