Research map / Vision-language and multimodal / Human and embodied modeling
Generating Easy-to-Understand Referring Expressions for Target Identifications
Mikihiro Tanaka, Takayuki Itamochi, Kenichi Narioka, Ikuro Sato, Yoshitaka Ushiku, Tatsuya Harada
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 |
|---|---|---|---|
| add local attention (ablation) | Our SR · RefGTA test | CIDEr: 0.557 -> 1.036 | Improved |
| add global attention (ablation) | Our SR · RefGTA test | CIDEr: 1.036 -> 1.036 | No clear effect |
| add sentinel attention (ablation) | Our SR · RefGTA test | CIDEr: 1.022 -> 1.036 | Improved |
| add local attention (ablation) | Our SR · RefCOCO Test A | CIDEr: 0.760 -> 0.865 | Improved |
| add ranking loss | Our SR · RefGTA test | R1-CIDEr: 1.065 -> 1.078 | Improved |
| add ranking loss to reinforcer | Our SR (Reinforcer) · RefGTA test | ranking accuracy: 55.46% -> 57.55% | Improved |
| add ranking loss to speaker | Our SR (Speaker) · RefGTA test | ranking accuracy: 56.38% -> 56.64% | Improved |
| add ranking loss | Our SR · RefGTA human evaluation | human comprehension accuracy (all): 71.52% -> 72.25% | Improved |
| add ranking loss | Our SR · RefGTA human evaluation | share ranked first (accuracy and time): 33.28% -> 35.86% | Improved |
| replace baseline with context-aware speaker (Our Speaker only) | re-SLR · RefGTA test | CIDEr: 0.966 -> 1.014 | Improved |
| add reranking | Our SR · RefCOCO Test A | CIDEr: 0.865 -> 0.842 | Hurt |
| add reranking | Our SR · RefCOCOg val | CIDEr: 0.738 -> 0.773 | Improved |
Closest papers by meaning
- Modeling Context in Referring Expressions (ECCV 2016 · similarity 0.90)
- A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era (NeurIPS 2024 · similarity 0.88)
- Comprehension-Guided Referring Expressions (CVPR 2017 · similarity 0.88)
- Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks (ICLR 2026 · similarity 0.86)
- RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension (AAAI 2025 · similarity 0.85)
- Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning (ICLR 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.
