Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.01668 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913083798061056 |
|---|---|
| author | Yin, Qian Wen, Di Peng, Kunyu Schneider, David Zhong, Zeyun Jaus, Alexander Marinov, Zdravko Wei, Jiale Liu, Ruiping Zheng, Junwei Chen, Yufan Zhang, Chen Qi, Lei Stiefelhagen, Rainer |
| author_facet | Yin, Qian Wen, Di Peng, Kunyu Schneider, David Zhong, Zeyun Jaus, Alexander Marinov, Zdravko Wei, Jiale Liu, Ruiping Zheng, Junwei Chen, Yufan Zhang, Chen Qi, Lei Stiefelhagen, Rainer |
| contents | Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correction is treated as an isolated edit, limiting reuse of information on annotator uncertainty and model reliability. We introduce IMPACT-Scribe, a correction-driven framework for dense labeling that uses each correction to improve future human-machine collaboration. IMPACT-Scribe combines uncertainty-aware boundary scribble supervision, local proposal modeling, cost-aware query planning, structured propagation, and correction-driven adaptation. Experiments and a human study show that this closed-loop design improves labeling quality per effort, enhances boundary accuracy, and fosters better human-machine interaction over time. The code will be made publicly available at https://github.com/BanzQians/IMPACT_AS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01668 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning Yin, Qian Wen, Di Peng, Kunyu Schneider, David Zhong, Zeyun Jaus, Alexander Marinov, Zdravko Wei, Jiale Liu, Ruiping Zheng, Junwei Chen, Yufan Zhang, Chen Qi, Lei Stiefelhagen, Rainer Computer Vision and Pattern Recognition Artificial Intelligence Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correction is treated as an isolated edit, limiting reuse of information on annotator uncertainty and model reliability. We introduce IMPACT-Scribe, a correction-driven framework for dense labeling that uses each correction to improve future human-machine collaboration. IMPACT-Scribe combines uncertainty-aware boundary scribble supervision, local proposal modeling, cost-aware query planning, structured propagation, and correction-driven adaptation. Experiments and a human study show that this closed-loop design improves labeling quality per effort, enhances boundary accuracy, and fosters better human-machine interaction over time. The code will be made publicly available at https://github.com/BanzQians/IMPACT_AS. |
| title | IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.01668 |