Research map / Vision-language and multimodal / Human and embodied modeling
Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and Queries
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 |
|---|---|---|---|
| add recurrent image-level attention to the baseline (ablation) | PLAN · RefCOCO TestA | accuracy: 77.45% -> 78.29% | Helped |
| add recurrent proposal-level attention to the baseline (ablation) | PLAN · RefCOCO TestA | accuracy: 77.45% -> 80.13% | Helped |
| combine image-level and proposal-level attention (ablation) | PLAN · RefCOCO TestA | accuracy: 80.13% -> 80.81% | Helped |
| add recurrent image-level attention to the baseline (ablation) | PLAN · RefCOCO+ TestA | accuracy: 63.48% -> 64.16% | Helped |
| add recurrent proposal-level attention to the baseline (ablation) | PLAN · RefCOCO+ TestA | accuracy: 63.48% -> 65.53% | Helped |
| combine image-level and proposal-level attention (ablation) | PLAN · RefCOCO+ TestA | accuracy: 65.53% -> 66.31 % | Helped |
| add recurrent image-level attention to the baseline (ablation) | PLAN · RefCOCOg val | accuracy: 66.05% -> 67.89% | Helped |
| add recurrent proposal-level attention to the baseline (ablation) | PLAN · RefCOCOg val | accuracy: 66.05% -> 68.54% | Helped |
| combine image-level and proposal-level attention (ablation) | PLAN · RefCOCOg val | accuracy: 68.54% -> 69.47% | Helped |
| add recurrent image-level attention to the baseline (ablation) | PLAN · GuessWhat?! val | classification error: 37.9% -> 37.4% | Helped |
| add recurrent proposal-level attention to the baseline (ablation) | PLAN · GuessWhat?! val | classification error: 37.9% -> 36.9% | Helped |
| combine image-level and proposal-level attention (ablation) | PLAN · GuessWhat?! test | classification error: 39.0% -> 36.6% | Helped |
Closest papers by meaning
- What's in the Image? A Deep-Dive into the Vision of Vision Language Models (CVPR 2025 · similarity 0.88)
- RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension (AAAI 2025 · similarity 0.88)
- Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning (ICLR 2026 · similarity 0.87)
- VisMin: Visual Minimal-Change Understanding (NeurIPS 2024 · similarity 0.87)
- A-VL: Adaptive Attention for Large Vision-Language Models (AAAI 2025 · similarity 0.87)
- Same or Not? Enhancing Visual Perception in Vision-Language Models (CVPR 2026 · similarity 0.87)
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.