Research map / Video / Video-language understanding
Straight to the Point: Fast-Forwarding Videos via Reinforcement Learning Using Textual Data
Washington Ramos, Michel Silva, Edson Araujo, Leandro Soriano Marcolino, Erickson Nascimento
Check 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 text-guided SFF-RL instead of SSFF | Instructional video fast-forwarding · YouCook2 test set | F1 Score: 0.18 -> 0.31 | Improved |
| Use text-guided SFF-RL instead of FFNet | Instructional video fast-forwarding · YouCook2 test set | F1 Score: 0.12 -> 0.31 | Improved |
| Use text-guided SFF-RL instead of SSFF | Instructional video fast-forwarding · YouCook2 test set | Recall: 0.15 -> 0.47 | Improved |
| Use text-guided SFF-RL instead of FFNet | Instructional video fast-forwarding · YouCook2 test set | Recall: 0.09 -> 0.47 | Improved |
| Use text-guided SFF-RL instead of SSFF | Instructional video fast-forwarding · YouCook2 test set | Precision: 0.22 -> 0.26 | Improved |
| Use text-guided SFF-RL instead of FFNet | Instructional video fast-forwarding · YouCook2 test set | Precision: 0.24 -> 0.26 | Improved |
| Use text-guided SFF-RL instead of SSFF and FFNet | Instructional video fast-forwarding · YouCook2 test set | Segment-level coverage | Improved |
| add word-level attention (ablation) | VDAN · Corresponding image-document pairs | Cosine similarity: 0.804 -> 0.807 | Improved |
| add word-level attention (ablation) | VDAN · Non-corresponding image-document pairs | Cosine similarity: 0.007 -> 0.006 | Improved |
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.
- FFNet — FFNet: Video Fast-Forwarding via Reinforcement Learning (CVPR 2018) · better on 3 of 3 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
- Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method (TPAMI 2022 · similarity 0.95)
- FFNet: Video Fast-Forwarding via Reinforcement Learning (CVPR 2018 · similarity 0.87)
- Efficient Frame Selection for Long Video Understanding via Reinforcement Learning (CVPR 2026 · similarity 0.86)
- VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis (ICLR 2025 · similarity 0.86)
- Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision (ICLR 2025 · similarity 0.84)
- Optical-Flow Guided Prompt Optimization for Coherent Video Generation (CVPR 2025 · similarity 0.84)
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.
