Research map / Video / Video-language understanding
Streamlined Dense Video Captioning
Jonghwan Mun, Linjie Yang, Zhou Ren, Ning Xu, Bohyung Han
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 |
|---|---|---|---|
| Select an ordered event sequence with ESGN instead of using all candidate proposals (ablation) | Dense video captioning · ActivityNet Captions validation | METEOR: 4.58 -> 6.73 | Improved |
| Select an ordered event sequence with ESGN instead of using all candidate proposals (ablation) | Event proposal selection · ActivityNet Captions validation | Number of proposals: 77.99 -> 2.85 | Improved |
| Add sequential captioning with episode-level context to independent captions (ablation) | ESGN captioning · ActivityNet Captions validation | METEOR: 6.73 -> 6.92 | Improved |
| Add reinforcement learning to sequential captioning (ablation) | ESGN-SCN · ActivityNet Captions validation | METEOR: 6.92 -> 8.82 | Improved |
| Use event- and episode-level rewards together rather than event-level reward alone (ablation) | SDVC reinforcement learning · ActivityNet Captions dataset | METEOR: 8.73 -> 8.82 | Improved |
| Add event-level reward to episode-level reward (ablation) | SDVC reinforcement learning · ActivityNet Captions dataset | METEOR: 8.29 -> 8.82 | Improved |
| Use ESGN rather than MFT for event sequence selection | Event proposal selection · ActivityNet Captions validation | Recall (average): 24.31 -> 55.58 | Improved |
| Use SDVC rather than MFT for dense captioning with learned proposals | Dense video captioning · ActivityNet Captions validation | METEOR: 7.08 -> 8.82 | Improved |
| Use SDVC rather than TDA-CG with learned proposals | Dense video captioning · ActivityNet Captions validation | BLEU@4: 1.31 -> 0.93 | Hurt |
| Use SDVC rather than Masked Transformer with GT proposals | Dense video captioning · ActivityNet Captions validation | CIDEr: 47.71 -> 43.48 | Hurt |
Closest papers by meaning
- An Efficient Framework for Dense Video Captioning (AAAI 2020 · similarity 0.95)
- Sketch, Ground, and Refine: Top-Down Dense Video Captioning (CVPR 2021 · similarity 0.94)
- Event-Equalized Dense Video Captioning (CVPR 2025 · similarity 0.91)
- Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-Learning (AAAI 2025 · similarity 0.89)
- DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement (CVPR 2024 · similarity 0.88)
- Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval (CVPR 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.
