Research map / Vision-language and multimodal / Human and embodied modeling
Visual Grounding via Accumulated Attention
Chaorui Deng, Qi Wu, Qingyao Wu, Fuyuan Hu, Fan Lyu, Mingkui Tan
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 A-ATT instead of the strongest listed baseline | Visual grounding model · ReferCOCO TestA | accuracy: 78.45 -> 81.67 | Improved |
| Use A-ATT instead of the strongest listed baseline | Visual grounding model · ReferCOCO TestB | accuracy: 80.10 vs. 80.01 | No clear effect |
| Use A-ATT instead of the strongest listed baseline | Visual grounding model · ReferCOCO+ TestA | accuracy: 63.34 -> 68.76 | Improved |
| Use A-ATT instead of the strongest listed baseline | Visual grounding model · ReferCOCOg Val | accuracy: 72.75 -> 73.18 | Improved |
| Use A-ATT with word2vector embeddings | GuessWhat?! grounding model · GuessWhat?! Test | error: 36.5% -> 34.2% | Improved |
| Add a second A-ATT round (ablation) | A-ATT visual grounding model · ReferCOCO TestA | accuracy: 79.67 -> 81.37 | Improved |
| Add a third A-ATT round (ablation) | A-ATT visual grounding model · ReferCOCO TestA | accuracy: 81.37 -> 81.67 | Improved |
| Add a fourth A-ATT round (ablation) | A-ATT visual grounding model · GuessWhat?! Test | error: 35.8% -> 36.3% | Hurt |
| Add query attention (ablation) | A-ATT visual grounding model · ReferCOCO TestA | accuracy: 79.14 -> 81.37 | Improved |
| Add image attention (ablation) | A-ATT visual grounding model · ReferCOCO TestA | accuracy: 79.82 -> 81.37 | Improved |
| Add object attention (ablation) | A-ATT visual grounding model · ReferCOCO TestA | accuracy: 80.08 -> 81.37 | Improved |
| Add interactions among query, image, and object attention (ablation) | A-ATT visual grounding model · ReferCOCO TestA | accuracy: 78.09 -> 81.37 | Improved |
Closest papers by meaning
- Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning (AAAI 2026 · similarity 0.90)
- Referencing Where to Focus: Improving Visual Grounding with Referential Query (NeurIPS 2024 · similarity 0.90)
- Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding (CVPR 2025 · similarity 0.90)
- Look Around Before Locating: Considering Content and Structure Information for Visual Grounding (AAAI 2025 · similarity 0.89)
- GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation (CVPR 2026 · similarity 0.88)
- GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models (AAAI 2026 · similarity 0.88)
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.
