Research map / Video / Video-language understanding
Title Generation for User Generated Videos
Kuo-Hao Zeng, Tseng-Hung Chen, Juan Carlos Niebles, Min Sun
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 highlight-sensitive captioning (HL-1) | S2VT · VTW | METEOR: 5.2 -> 6.1 | Improved |
| add iterative refinement (HL over HL-1) (ablation) | S2VT · VTW | CIDEr: 23.0 -> 24.9 | Improved |
| add highlight-sensitive captioning (HL) | SA · VTW | CIDEr: 18.5 -> 24.9 | Improved |
| use ground-truth highlight clips at evaluation without highlight training (ablation) | S2VT · VTW | METEOR: 5.2 -> 5.1 | No clear effect |
| train highlight captioner without highlight supervision (HL-0 vs Vanilla) (ablation) | S2VT · VTW | CIDEr: 18.6 -> 22.4 | Improved |
| treat descriptions as extra title sentences with their videos (ablation) | S2VT · VTW | CIDEr: 18.6 -> 12.0 | Hurt |
| treat descriptions as extra title sentences with their videos (ablation) | SA · VTW | CIDEr: 18.5 -> 18.9 | No clear effect |
| add description sentences as augmented sentence-only examples | S2VT · VTW | CIDEr: 18.6 -> 21.6 | Improved |
| add web-retrieved sentence augmentation | S2VT · VTW | CIDEr: 18.6 -> 22.8 | Improved |
| add web-retrieved sentence augmentation | SA · VTW | CIDEr: 18.5 -> 22.2 | Improved |
| combine HL with Web Aug. | S2VT · VTW | CIDEr: 24.9 -> 25.4 | Improved |
| combine HL with Web Aug. | SA · VTW | CIDEr: 24.9 -> 25.1 | Improved |
Closest papers by meaning
- Chinese Title Generation for Short Videos: Dataset, Metric and Algorithm (TPAMI 2024 · similarity 0.89)
- AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark (ICLR 2025 · similarity 0.86)
- Video ReCap: Recursive Captioning of Hour-Long Videos (CVPR 2024 · similarity 0.86)
- InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption (CVPR 2025 · similarity 0.86)
- Distilling Vision-Language Models on Millions of Videos (CVPR 2024 · similarity 0.86)
- Set Prediction Guided by Semantic Concepts for Diverse Video Captioning (AAAI 2024 · similarity 0.85)
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.
