Research map / Video / Action recognition
Three Birds with One Stone: Multi-Task Temporal Action Detection via Recycling Temporal Annotations
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 both annotation-recycled auxiliary tasks (ablation) | R-C3D temporal action detector · THUMOS’14 | mAP@0.5: 28.9 -> 31.9 | Helped |
| add multi-action classification (ablation) | R-C3D temporal action detector · THUMOS’14 | mAP@0.5: 28.9 -> 31.1 | Helped |
| add localisation confidence estimation (ablation) | R-C3D temporal action detector · THUMOS’14 | mAP@0.5: 28.9 -> 30.5 | Helped |
| add both annotation-recycled auxiliary tasks (ablation) | R-C3D temporal action detector · ActivityNet v1.3 validation | Average mAP: 12.7 -> 14.5 | Helped |
| add multi-action classification (ablation) | R-C3D temporal action detector · ActivityNet v1.3 validation | Average mAP: 12.7 -> 14.2 | Helped |
| add localisation confidence estimation (ablation) | R-C3D temporal action detector · ActivityNet v1.3 validation | Average mAP: 12.7 -> 13.5 | Helped |
| add both annotation-recycled auxiliary tasks (ablation) | R-C3D temporal action detector · Charades | mAP (standard): 12.4 -> 14.6 | Helped |
| add multi-action classification (ablation) | R-C3D temporal action detector · Charades | mAP (standard): 12.4 -> 14.3 | Helped |
| add localisation confidence estimation (ablation) | R-C3D temporal action detector · Charades | mAP (standard): 12.4 -> 14.1 | Helped |
| add both auxiliary tasks and prediction refinement (ablation) | R-C3D temporal action detector · THUMOS’14 | mAP@0.5: 28.9 -> 31.9 | Helped |
| add prediction refinement (ablation) | R-C3D temporal action detector · THUMOS’14 | mAP@0.5: 28.9 -> 29.8 | Helped |
| add auxiliary-task training (ablation) | R-C3D temporal action detector · THUMOS’14 | mAP@0.5: 28.9 -> 30.2 | Helped |
Closest papers by meaning
- Learning To Refactor Action and Co-Occurrence Features for Temporal Action Localization (CVPR 2022 · similarity 0.91)
- Temporal Action Localization by Structured Maximal Sums (CVPR 2017 · similarity 0.91)
- Temporal Action Localization in Untrimmed Videos via Multi-Stage CNNs (CVPR 2016 · similarity 0.90)
- Rethinking the Faster R-CNN Architecture for Temporal Action Localization (CVPR 2018 · similarity 0.90)
- Modeling Multi-Label Action Dependencies for Temporal Action Localization (CVPR 2021 · similarity 0.90)
- Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature (AAAI 2024 · similarity 0.89)
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.