Research map / Vision-language and multimodal / Human and embodied modeling
Interpretable and Globally Optimal Prediction for Textual Grounding using Image Concepts
Read the paperCheck 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 the full Prior + Geo + Seg + Det model instead of CCA | Textual grounding · Flickr 30k Entities | accuracy: 50.89 -> 51.63 | Helped |
| Add detection maps plus body-part detection to Prior + Geo + Seg + Det (ablation) | Textual grounding · Flickr 30k Entities | accuracy: 51.63 -> 53.97 | Helped |
| Add segmentation maps to word priors and geometric features (ablation) | Textual grounding · ReferItGame | accuracy: 25.56 -> 33.36 | Helped |
| Add detection maps to Prior + Geo + Seg (ablation) | Textual grounding · ReferItGame | accuracy: 33.36 -> 34.70 | Helped |
| Use the full model instead of GroundeR | Textual grounding · ReferItGame | accuracy: 23.44 -> 34.70 | Helped |
| Use the full model instead of CCA | Textual grounding · Flickr 30k Entities: people | accuracy: 64.73 -> 68.71 | Helped |
| Use the full model instead of CCA | Textual grounding · Flickr 30k Entities: clothing | accuracy: 46.88 -> 46.83 | Hurt |
| Use the full model instead of CCA | Textual grounding · Flickr 30k Entities: body parts | accuracy: 17.21 -> 19.50 | Helped |
| Use the full model instead of CCA | Textual grounding · Flickr 30k Entities: animals | accuracy: 65.83 -> 70.07 | Helped |
| Use the full model instead of CCA | Textual grounding · Flickr 30k Entities: vehicles | accuracy: 68.75 -> 73.75 | Helped |
| Use the full model instead of CCA | Textual grounding · Flickr 30k Entities: instruments | accuracy: 37.65 -> 39.50 | Helped |
| Use the full model instead of CCA | Textual grounding · Flickr 30k Entities: scene | accuracy: 51.39 -> 60.38 | Helped |
Closest papers by meaning
- Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning (AAAI 2026 · similarity 0.87)
- Comprehensive Visual Grounding for Video Description (AAAI 2024 · similarity 0.86)
- GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation (CVPR 2026 · similarity 0.86)
- Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding (CVPR 2025 · similarity 0.86)
- GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models (AAAI 2026 · similarity 0.86)
- Enhancing Part-Level Point Grounding for Any Open-Source MLLMs (CVPR 2026 · similarity 0.85)
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.