Research map / Video / Video-language understanding
Aligning Source Visual and Target Language Domains for Unpaired Video Captioning
Fenglin Liu, Xian Wu, Chenyu You, Shen Ge, Yuexian Zou, Xu 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 VIM with pseudo supervised training (ablation) | Base Model · MSR-VTT (unpaired) | CIDEr: 36.3 -> 40.7 | Improved |
| add adversarial loss L_adv to VIM (ablation) | Base Model + VIM · MSR-VTT (unpaired) | CIDEr: 40.7 -> 42.0 | Improved |
| add reverse adversarial and cycle losses (ablation) | Base Model + VIM · MSR-VTT (unpaired) | CIDEr: 42.0 -> 42.3 | Improved |
| add MCE encoder to VIM (ablation) | UVC-VI · MSR-VTT (unpaired) | CIDEr: 42.3 -> 44.5 | Improved |
| add MCE encoder to VIM (ablation) | UVC-VI · MSR-VTT (unpaired) | BLEU-4: 38.5 -> 38.9 | Improved |
| add VIM to base pipeline (ablation) | Base Model · MSR-VTT (unpaired) | SPICE Attributes: 1.9 -> 2.4 | Improved |
| add VIM to base pipeline (ablation) | Base Model · MSR-VTT (unpaired) | SPICE Color: 0.1 -> 0.6 | Improved |
| add MCE to VIM (ablation) | UVC-VI · MSR-VTT (unpaired) | SPICE Objects: 13.3 -> 13.9 | Improved |
| add MCE to Attention-LSTM (ablation) | Attention-LSTM · MSVD (supervised) | CIDEr: 88.5 -> 93.4 | Improved |
| add MCE to Attention-LSTM (ablation) | Attention-LSTM · MSR-VTT (supervised) | CIDEr: 48.9 -> 52.6 | Improved |
| add MCE to Transformer (ablation) | Transformer · MSVD (supervised) | CIDEr: 91.2 -> 97.7 | Improved |
| add MCE to Transformer (ablation) | Transformer · MSR-VTT (supervised) | CIDEr: 49.3 -> 54.6 | Improved |
Closest papers by meaning
- Unpaired Image Captioning by Language Pivoting (ECCV 2018 · similarity 0.90)
- Distilling Vision-Language Models on Millions of Videos (CVPR 2024 · similarity 0.89)
- VideoCon: Robust Video-Language Alignment via Contrast Captions (CVPR 2024 · similarity 0.87)
- Video ReCap: Recursive Captioning of Hour-Long Videos (CVPR 2024 · similarity 0.86)
- VidLA: Video-Language Alignment at Scale (CVPR 2024 · similarity 0.86)
- Can Text-to-Video Generation help Video-Language Alignment? (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.
