Research map / Video / Video-language understanding
Exploring Group Video Captioning with Efficient Relational Approximation
Wang Lin, Tao Jin, Ye Wang, Wenwen Pan, Linjun Li, Xize Cheng, Zhou Zhao
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 |
|---|---|---|---|
| use ERA instead of traversal for shared content identification | group video captioning model · YouCook2 Captions | training time per epoch: 3884.4s -> 17.6s | Improved |
| use ERA instead of traversal on caption quality | group video captioning model · YouCook2 Captions | CIDEr: 179.4 -> 180.8 | No clear effect |
| use ERA instead of simple averaging of video features | group video captioning model · YouCook2 Captions | CIDEr: +10.2% CIDEr (170.6 -> 180.8) | Improved |
| add contextual feature refinery instead of subtraction (ablation) | ERA captioner · YouCook2 Captions | CIDEr: 168.3 -> 178.7 | Improved |
| add contextual features (subtraction) to ERA captioner (ablation) | ERA captioner · YouCook2 Captions | CIDEr: 161.7 -> 168.3 | Improved |
| add intra-group contrastive loss (IGC) on top of refinery (ablation) | ERA captioner · YouCook2 Captions | CIDEr: 178.7 -> 180.8 | Improved |
| add IGC on top of refinery for ERA (ablation) | ERA captioner · YouCook2 Captions | WER: 75.42 -> 75.77 | No clear effect |
| add IGC on top of refinery for Traversal (ablation) | Traversal captioner · ActivityNet Captions | BLEU4: 17.65 -> 16.53 | Mixed |
| remove reference videos from the group (ablation) | ERA captioner · YouCook2 Captions | CIDEr: 180.8 -> 69.81 | Hurt |
| reduce number of target videos from 3 to 1 (ablation) | ERA captioner · YouCook2 Captions | CIDEr: 180.8 -> 163.1 | Hurt |
Closest papers by meaning
- Context-Aware Group Captioning via Self-Attention and Contrastive Features (CVPR 2020 · similarity 0.88)
- GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints (CVPR 2018 · similarity 0.87)
- Semantic Grouping Network for Video Captioning (AAAI 2021 · similarity 0.87)
- Fine-Grained Captioning of Long Videos through Scene Graph Consolidation (ICML 2025 · similarity 0.85)
- Video ReCap: Recursive Captioning of Hour-Long Videos (CVPR 2024 · similarity 0.84)
- Progress-Aware Video Frame Captioning (CVPR 2025 · similarity 0.83)
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.
