Research map / Video / Video-language understanding
Joint Syntax Representation Learning and Visual Cue Translation for Video Captioning
Jingyi Hou, Xinxiao Wu, Wentian Zhao, Jiebo Luo, Yunde Jia
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 POS tagging and mixture model to the S2S baseline (ablation) | ConvCap S2S baseline · MSVD | CIDEr: 77.0 -> 87.8 | Improved |
| add mixture model for word generation instead of a softmax classifier (ablation) | Ours · MSVD | CIDEr: 82.1 -> 87.8 | Improved |
| add video POS tagging (ablation) | Ours · MSVD | CIDEr: 85.6 -> 87.8 | Improved |
| add constraint term Lc encouraging POS variety (ablation) | Ours · MSVD | CIDEr: 83.3 -> 87.8 | Improved |
| add constraint term Lc (ablation) | Ours · MSVD | B@4: 51.3 -> 52.8 | Improved |
| add video POS tagging (ablation) | Ours · MSVD | METEOR: 35.1 -> 36.1 | Improved |
| add mixture model (ablation) | Ours · MSVD | METEOR: 34.3 -> 34.3 | No clear effect |
| proposed method versus best prior on MSR-VTT B@4 | Ours · MSR-VTT | B@4: 41.3 -> 42.3 | Improved |
| proposed method versus SDVC on ActivityNet | Ours · ActivityNet Captions val | METEOR: 13.1 -> 11.3 | Hurt |
| proposed method versus GRU-EVE on MSR-VTT | Ours · MSR-VTT | CIDEr: 48.1 -> 49.1 | Improved |
Closest papers by meaning
- PercepCap: Video Captioner with Structured Spatio-Temporal Perception (NeurIPS 2026 · similarity 0.88)
- Distilling Vision-Language Models on Millions of Videos (CVPR 2024 · similarity 0.88)
- Video ReCap: Recursive Captioning of Hour-Long Videos (CVPR 2024 · similarity 0.86)
- Progress-Aware Video Frame Captioning (CVPR 2025 · similarity 0.86)
- VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models (CVPR 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.
