Research map / Video / Video-language understanding
Refined Semantic Enhancement towards Frequency Diffusion for Video Captioning
Xian Zhong, Zipeng Li, Shuqin Chen, Kui Jiang, Chen Chen, Mang Ye
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 FAD and DSS to the AR-B baseline | AR-B · MSR-VTT | CIDEr: 51.1 -> 53.1 | Improved |
| Add FAD and DSS to the AR-B baseline | AR-B · MSVD | CIDEr: 91.4 -> 96.7 | Improved |
| Add FAD without DSS (ablation) | AR-B · MSR-VTT | CIDEr: 51.1 -> 52.9 | Improved |
| Add FAD without DSS (ablation) | AR-B · MSVD | CIDEr: 91.4 -> 94.1 | Improved |
| Add DSS without FAD (ablation) | AR-B · MSR-VTT | CIDEr: 51.1 -> 52.2 | Improved |
| Add DSS without FAD (ablation) | AR-B · MSVD | CIDEr: 91.4 -> 93.1 | Improved |
| Combine FAD and DSS rather than use FAD alone (ablation) | RSFD · MSR-VTT | CIDEr: 52.9 -> 53.1 | Improved |
| Combine FAD and DSS rather than use FAD alone (ablation) | RSFD · MSVD | CIDEr: 94.1 -> 96.7 | Improved |
| Use DSS supervision window size 5 instead of 3 (ablation) | RSFD · MSR-VTT | CIDEr: 52.2 -> 53.1 | Improved |
| Increase DSS supervision window from size 5 to 7 (ablation) | RSFD · MSR-VTT | CIDEr: 53.1 -> 51.9 | Hurt |
| Increase DSS supervision window from size 5 to 9 (ablation) | RSFD · MSR-VTT | CIDEr: 53.1 -> 51.6 | Hurt |
| Use DSS supervision window size 5 instead of 3 (ablation) | RSFD · MSVD | CIDEr: 94.1 -> 96.7 | Improved |
Closest papers by meaning
- Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation (CVPR 2025 · similarity 0.87)
- Mimir: Improving Video Diffusion Models for Precise Text Understanding (CVPR 2025 · similarity 0.87)
- Distilling Vision-Language Models on Millions of Videos (CVPR 2024 · similarity 0.86)
- Generative Video Diffusion for Unseen Novel Semantic Video Moment Retrieval (AAAI 2025 · similarity 0.86)
- AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark (ICLR 2025 · similarity 0.86)
- Fine-Grained Captioning of Long Videos through Scene Graph Consolidation (ICML 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.
