Research map / Video / Action recognition
Event-Guided Procedure Planning from Instructional Videos with Text Supervision
An-Lan Wang, Kun-Yu Lin, Jia-Run Du, Jingke Meng, Wei-Shi Zheng
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 Event-aware Prompt Generator (ablation) | E3P · CrossTask (T=3) | Success Rate: 23.55 -> 25.62 | Improved |
| add Action Relation Mining module (ablation) | E3P · CrossTask (T=4) | Success Rate: 14.85 -> 16.49 | Improved |
| add prompting-based feature extractor to the action classifier baseline (ablation) | baseline · CrossTask (T=3) | Success Rate: 22.56 -> 23.55 | Improved |
| add Event-aware Prompt Generator to full model without it (ablation) | E3P · CrossTask (T=4) | Success Rate: 14.23 -> 16.49 | Improved |
| add DropRelation regularization (drop rate 20%) to ARM (ablation) | E3P · CrossTask (T=4) | Success Rate: 15.69 -> 16.49 | Improved |
| increase DropRelation rate beyond optimum (40%) (ablation) | E3P · CrossTask (T=3) | Success Rate: 26.40 -> 25.76 | Hurt |
| use pre-trained CLIP text encoder with hand-crafted prompts (ablation) | E3P · CrossTask (T=4) | Success Rate: 14.70 -> 16.49 | Improved |
| add ARM to reduce action transition matrix error (ablation) | E3P · CrossTask (T=4) | mean Absolute Error: 3.21 -> 2.55 | Improved |
| event-guided paradigm instead of direct state-to-action prediction | text-supervised procedure planning · COIN (T=3) | Success Rate: 15.40 -> 19.57 | Improved |
| E3P vs P3IV on mIoU for CrossTask T=3 | E3P · CrossTask (T=3) | mIoU: 73.89 -> 74.05 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- P3IV — P3IV: Probabilistic Procedure Planning From Instructional Videos With Weak Supervision (CVPR 2022) · better on 9 of 9 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Toward Accurate Procedure Planning in Instructional Videos: Visual State Generation Helps Task-Selective Diffusion (TPAMI 2025 · similarity 0.92)
- P3IV: Probabilistic Procedure Planning From Instructional Videos With Weak Supervision (CVPR 2022 · similarity 0.91)
- SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos (ICLR 2024 · similarity 0.91)
- Procedure Knowledge Decoupled Distillation Strategy for Procedure Planning in Instructional Videos (AAAI 2025 · similarity 0.90)
- Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos (ICLR 2025 · similarity 0.89)
- Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos (CVPR 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.
