Research map / Video / Action recognition
PDPP:Projected Diffusion for Procedure Planning in Instructional Videos
Hanlin Wang, Yilu Wu, Sheng Guo, Limin Wang
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 |
|---|---|---|---|
| Use PDPP instead of P3IV | procedure planning · CrossTask T=3 | SR: 23.34 -> 37.20 | Improved |
| Use PDPP instead of P3IV | procedure planning · NIV T=4 | mAcc: 38.36 -> 48.92 | Improved |
| Use PDPP instead of P3IV | procedure planning · COIN T=3 | mAcc: 21.67 -> 45.62 | Improved |
| Add task-class supervision (ablation) | PDPP · COIN T=3 | SR: 16.46 -> 21.33 | Improved |
| Add task-class supervision (ablation) | PDPP · COIN T=4 | SR: 12.32 -> 14.41 | Improved |
| Add task-class supervision (ablation) | PDPP · NIV T=4 | SR: 26.72 -> 26.72 | No clear effect |
| Remove the diffusion process and sample noise in one shot (ablation) | PDPP · CrossTaskHow T=6 | ModeRec: 11.04 -> 22.68 | Hurt |
| Use deterministic zero initialization instead of random diffusion sampling (ablation) | PDPP · CrossTaskHow T=6 | ModeRec: 6.75 -> 22.68 | Hurt |
| Use random diffusion sampling rather than deterministic zero initialization (ablation) | PDPP · CrossTaskHow T=3 | SR: 39.03 -> 37.20 | Hurt |
| Use random diffusion sampling rather than deterministic zero initialization (ablation) | PDPP · CrossTaskHow T=3 | ModeRec: 34.13 -> 36.49 | Improved |
Later papers that compared with this method
1 later accepted paper reports PDPP as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- RAP: Retrieval-Augmented Planner for Adaptive Procedure Planning in Instructional Videos (ECCV 2024 · better on 1 of 2 shared results)
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 11 of 17 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
- Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos (ICLR 2025 · similarity 0.90)
- Procedure Knowledge Decoupled Distillation Strategy for Procedure Planning in Instructional Videos (AAAI 2025 · similarity 0.90)
- Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos (CVPR 2024 · similarity 0.89)
- SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos (ICLR 2024 · similarity 0.88)
- ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions (CVPR 2025 · similarity 0.88)
- PlanLLM: Video Procedure Planning with Refinable Large Language Models (AAAI 2025 · similarity 0.85)
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.
