Research map / Vision-language and multimodal / Human and embodied modeling
Human-Like Controllable Image Captioning With Verb-Specific Semantic Roles
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 verb-specific semantic roles as the caption control signal | VSR-guided CIC · COCO Entities, GSRL proposals | CIDEr-D: 127.6 -> 162.8 | Helped |
| Use verb-specific semantic roles as the caption control signal | VSR-guided CIC · Flickr30K Entities, GSRL proposals | CIDEr-D: 58.7 -> 71.6 | Helped |
| Use verb-specific semantic roles as the caption control signal | VSR-guided CIC · COCO Entities, GT proposals | CIDEr-D: 191.3 -> 235.1 | Helped |
| Use verb-specific semantic roles as the caption control signal | VSR-guided CIC · Flickr30K Entities, GT proposals | CIDEr-D: 82.0 -> 97.5 | Helped |
| Add verb information to SSP and caption generation (ablation) | VSR-guided CIC · COCO Entities, GSRL proposals | CIDEr-D: 129.5 -> 162.8 | Helped |
| Add verb information to SSP and caption generation (ablation) | VSR-guided CIC · Flickr30K Entities, GSRL proposals | CIDEr-D: 50.8 -> 71.6 | Helped |
| Add verb information to SSP and caption generation (ablation) | VSR-guided CIC · COCO Entities, GT proposals | CIDEr-D: 199.5 -> 235.1 | Helped |
| Add verb information to SSP and caption generation (ablation) | VSR-guided CIC · Flickr30K Entities, GT proposals | CIDEr-D: 82.2 -> 97.5 | Helped |
| Provide oracle-format verb output | VSR-guided CIC · COCO Entities, GSRL proposals | CIDEr-D: 162.8 -> 184.3 | Helped |
| Provide oracle-format verb output | VSR-guided CIC · Flickr30K Entities, GSRL proposals | CIDEr-D: 71.6 -> 96.5 | Helped |
| Provide oracle-format verb output | VSR-guided CIC · COCO Entities, GT proposals | CIDEr-D: 235.1 -> 265.0 | Helped |
| Provide oracle-format verb output | VSR-guided CIC · Flickr30K Entities, GT proposals | CIDEr-D: 97.5 -> 131.4 | Helped |
Closest papers by meaning
- CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness (NeurIPS 2025 · similarity 0.84)
- Enhancing Descriptive Captions with Visual Attributes for Multimodal Perception (CVPR 2026 · similarity 0.84)
- CaptionQA: Is Your Caption as Useful as the Image Itself? (CVPR 2026 · similarity 0.84)
- CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning (ICLR 2026 · similarity 0.84)
- Top-Down Semantic Refinement for Image Captioning (AAAI 2026 · similarity 0.84)
- Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning (ICLR 2025 · similarity 0.84)
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.