Research map / Vision-language and multimodal / Human and embodied modeling
GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints
Fuhai Chen, Rongrong Ji, Xiaoshuai Sun, Yongjian Wu, Jinsong Su
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 structured relevance and diversity constraints to GroupCap (ablation) | GroupCap-T captioner · FG-dataset | B4: 32.9 -> 33.0 | Improved |
| Add the structured relevance constraint (ablation) | GroupCap-T-SDC · FG-dataset | B4: 32.8 -> 33.0 | Improved |
| Add the structured diversity constraint (ablation) | GroupCap-T-SRC · FG-dataset | B4: 33.0 -> 33.0 | No clear effect |
| Add the structured relevance constraint (ablation) | GroupCap-T-SDC · ES-dataset | B4: 31.2 -> 31.6 | Improved |
| Add the structured diversity constraint (ablation) | GroupCap-T-SRC · ES-dataset | B4: 31.5 -> 31.6 | Improved |
| Add the full GroupCap constraint system to the unconstrained model (ablation) | GroupCap-T · ES-dataset | B4: 31.1 -> 31.6 | Improved |
| Use an ensemble (ablation) | GroupCap · FG-dataset | B4: 33.0 -> 33.8 | Improved |
| Use the ternary VP-Tree with relation mapping instead of the original VP-Tree (ablation) | GroupCap parser · FG-dataset | B4: 32.8 -> 32.9 | Improved |
| Train with grouped images rather than ungrouped images | SCN · FG-dataset | B4: 33.0 -> 33.0 | No clear effect |
Closest papers by meaning
- ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning (AAAI 2025 · similarity 0.86)
- MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites (ICLR 2026 · similarity 0.86)
- Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning (CVPR 2025 · similarity 0.86)
- CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness (NeurIPS 2025 · similarity 0.86)
- Fine-Grained Captioning of Long Videos through Scene Graph Consolidation (ICML 2025 · similarity 0.86)
- FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity (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.
