Research map / Video / Video-language understanding
Video Captioning via Hierarchical Reinforcement Learning
Read the paperCheck 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 |
|---|---|---|---|
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · MSR-VTT | CIDEr: 46.3 -> 48.0 | Helped |
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · MSR-VTT | BLEU@4: 40.6 -> 41.3 | Helped |
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · MSR-VTT | METEOR: 28.5 -> 28.7 | Helped |
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · MSR-VTT | ROUGE-L: 60.7 -> 61.7 | Helped |
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · Charades Captions | BLEU@1: 57.6 -> 64.4 | Helped |
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · Charades Captions | BLEU@2: 41.4 -> 44.3 | Helped |
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · Charades Captions | BLEU@3: 28.0 -> 29.4 | Helped |
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · Charades Captions | BLEU@4: 18.8 -> 18.8 | No clear effect |
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · Charades Captions | METEOR: 17.7 -> 19.5 | Helped |
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · Charades Captions | ROUGE-L: 39.8 -> 41.4 | Helped |
| Replace a flat policy-gradient captioner with hierarchical Manager–Worker captioning | Video captioning · Charades Captions | CIDEr: 21.6 -> 23.2 | Helped |
| Increase latent goal dimension from 16 to 32 (ablation) | HRL · Charades Captions | BLEU@1: 64.4 -> 64.0 | Hurt |
Closest papers by meaning
- Video ReCap: Recursive Captioning of Hour-Long Videos (CVPR 2024 · similarity 0.87)
- CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning (ICLR 2026 · similarity 0.87)
- Progress-Aware Video Frame Captioning (CVPR 2025 · similarity 0.87)
- BalCapRL : A Balanced Framework for RL-Based MLLM Image Captioning (NeurIPS 2026 · similarity 0.86)
- Vript: A Video Is Worth Thousands of Words (NeurIPS 2024 · similarity 0.86)
- VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models (CVPR 2025 · similarity 0.86)
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.