Research map / Vision-language and multimodal / Human and embodied modeling
A Joint Speaker-Listener-Reinforcer Model for Referring Expressions
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 |
|---|---|---|---|
| jointly train the speaker with the listener (ablation) | speaker comprehension model · RefCOCO val | accuracy: 69.95% -> 71.20% | Helped |
| add the reinforcer to joint speaker-listener training (ablation) | speaker comprehension model · RefCOCO val | accuracy: 71.20% -> 72.46% | Helped |
| add MMI ranking (ablation) | speaker+listener+reinforcer comprehension model · RefCOCO val | accuracy: 72.46% -> 79.56% | Helped |
| jointly train the listener with the speaker (ablation) | listener comprehension model · RefCOCO val | accuracy: 77.48% -> 77.84% | Helped |
| ensemble speaker and listener predictions (ablation) | speaker+listener+reinforcer+MMI comprehension model · RefCOCO val | accuracy: 78.36% -> 80.36% | Helped |
| add reranking and global optimization over generated expressions (ablation) | speaker+listener+reinforcer+MMI generation model · RefCOCO TestA | human click accuracy: 74.08% -> 76.95% | Helped |
| add reranking (ablation) | speaker+listener+reinforcer+MMI generation model · RefCOCO TestA | METEOR: 0.268 -> 0.296 | Helped |
| add the reinforcer (ablation) | speaker+listener+MMI generation model with reranking · RefCOCO TestA | METEOR: 0.293 -> 0.296 | Helped |
| add the reinforcer (ablation) | speaker+listener+MMI listener comprehension model · RefCOCO val | accuracy: 77.84% -> 78.14% | Mixed |
Closest papers by meaning
- Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks (ICLR 2026 · similarity 0.87)
- RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension (AAAI 2025 · similarity 0.86)
- Revisiting Counterfactual Problems in Referring Expression Comprehension (CVPR 2024 · similarity 0.86)
- Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point (AAAI 2024 · similarity 0.85)
- A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era (NeurIPS 2024 · similarity 0.85)
- Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension (AAAI 2025 · 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.