Research map / Video / Video-language understanding
Weakly Supervised Dense Event Captioning in Videos
Xuguang Duan, Wenbing Huang, Chuang Gan, Jingdong Wang, Wenwu Zhu, Junzhou Huang
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 anchor classification to the weakly supervised method (ablation) | Ours · ActivityNet Captions | METEOR: 6.08 -> 6.30 | Improved |
| add anchor classification to the weakly supervised method (ablation) | Ours · ActivityNet Captions | CIDEr: 15.1 -> 18.77 | Improved |
| add anchor classification to the weakly supervised method (ablation) | Ours · ActivityNet Captions | Bleu@4: 0.80 -> 1.27 | Improved |
| add anchor regression to the weakly supervised method (ablation) | Ours · ActivityNet Captions | METEOR: 6.11 -> 6.30 | Improved |
| add anchor regression to the weakly supervised method (ablation) | Ours · ActivityNet Captions | CIDEr: 17.66 -> 18.77 | Hurt |
| add anchor regression to the weakly supervised method (ablation) | Ours · ActivityNet Captions | Bleu@4: 1.44 -> 1.27 | Hurt |
| train with the weakly supervised cycle rather than only using the pretrained caption generator (ablation) | Ours · ActivityNet Captions | METEOR: 4.58 -> 6.30 | Improved |
| train with the weakly supervised cycle rather than only using the pretrained caption generator (ablation) | Ours · ActivityNet Captions | CIDEr: 10.45 -> 18.77 | Improved |
| train with the weakly supervised cycle rather than only using the pretrained caption generator (ablation) | Ours · ActivityNet Captions | Bleu@4: 0.69 -> 1.27 | Improved |
| use the weakly supervised sentence localizer instead of CTRL | Sentence localization · ActivityNet Captions | R@1, IoU 0.3: 28.70 -> 41.98 | Improved |
Closest papers by meaning
- Towards Bridging Event Captioner and Sentence Localizer for Weakly Supervised Dense Event Captioning (CVPR 2021 · similarity 0.95)
- Event-Equalized Dense Video Captioning (CVPR 2025 · similarity 0.93)
- Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning (AAAI 2025 · similarity 0.91)
- Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-Learning (AAAI 2025 · similarity 0.90)
- Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval (CVPR 2024 · similarity 0.88)
- Dense Video Object Captioning from Disjoint Supervision (ICLR 2025 · similarity 0.88)
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.
