Research map / Video / Action recognition
RAP: Retrieval-Augmented Planner for Adaptive Procedure Planning in Instructional Videos
Ali Zare, Yulei Niu, Hammad Ayyubi, Shih-Fu Chang
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 retrieval-augmented memory to the base planner (T=3) (ablation) | RAP · CrossTask T=3 | SR: 25.42 -> 29.23 | Improved |
| add retrieval memory in variable-length setting (ablation) | RAP · CrossTask variable length | SR: 18.54 -> 20.28 | Improved |
| add retrieval memory on COIN variable length (ablation) | RAP · COIN variable length | SR: 17.86 -> 19.14 | Improved |
| add weakly-supervised pseudo-labelled unannotated videos (100%) (ablation) | RAP · CrossTask variable length | SR: 20.28 -> 21.79 | Improved |
| use only 25% of unannotated data (ablation) | RAP · CrossTask variable length | SR: 20.28 -> 19.20 | Hurt |
| add unannotated data at T=4 | RAP · CrossTask T=4 | mIoU: 71.49 -> 71.33 | No clear effect |
| use explicit retrieval memory instead of implicit memory (ablation) | RAP · CrossTask T=3 | SR: 26.78 -> 29.23 | Improved |
| use END token instead of separate length predictor (ablation) | RAP · CrossTask variable length | plan-length accuracy (%): 21.32 -> 53.47 | Improved |
| retrieval head alone vs base planner (ablation) | RAP · CrossTask variable length | SR: 18.54 -> 11.42 | Hurt |
| increase datastore size from 1000 to 1500 (ablation) | RAP · CrossTask variable length | SR: 20.28 -> 18.03 | Hurt |
| change lambda from 0.1 to 0.05 or 0.15 (ablation) | RAP · CrossTask variable length | SR: 20.28 -> 19.86 | No clear effect |
| RAP vs Skip-Plan/PDPP on COIN T=4 mAcc | RAP · COIN T=4 | mAcc: 44.10 vs 42.11 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- Skip-Plan — Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning (ICCV 2023) · better on 5 of 5 shared results
- PDPP — PDPP:Projected Diffusion for Procedure Planning in Instructional Videos (CVPR 2023) · better on 1 of 2 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
- Event-Guided Procedure Planning from Instructional Videos with Text Supervision (ICCV 2023 · similarity 0.91)
- Procedure Knowledge Decoupled Distillation Strategy for Procedure Planning in Instructional Videos (AAAI 2025 · similarity 0.90)
- SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos (ICLR 2024 · 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 0.88)
- Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis (AAAI 2024 · similarity 0.87)
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.
