Research map / Vision-language and multimodal / Human and embodied modeling
Referring Expression Comprehension Using Language Adaptive Inference
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 language-conditioned dynamic subnets with joint layer and filter selection instead of a fixed REC network | LADS · RefCOCO, RefCOCO+, RefCOCOg, Referit | Prec@0.5: +2.15%/ +2.67%/ +2.53% on RefCOCO; +2.91%/ +3.96%/ +0.40% on RefCOCO+; +1.01%/ +1.04% on RefCOCOg | Helped |
| Use language-conditioned dynamic subnets with joint layer and filter selection instead of a fixed REC network | LADS · RefCOCO, RefCOCO+, RefCOCOg, Referit | Prec@0.5: +2.53%/ +4.00%/ +0.45% on RefCOCO; +7.66%/ +9.49%/ +4.19% on RefCOCO+; +3.90%/ +4.22% on RefCOCOg; +1.32% on Referit | Helped |
| Use LADS rather than the reported competing methods | LADS · All datasets (average over referring expressions) | inference time (ms): 20ms | Helped |
| Pre-train on the large-scale referring-expression dataset before fine-tuning | LADS · RefCOCO, RefCOCO+, RefCOCOg, Referit | Prec@0.5 | Helped |
| Pre-train on the large-scale referring-expression dataset before fine-tuning | LADS · All datasets (average over referring expressions) | inference time (ms): 20ms to 18ms; 2ms speedup | Helped |
Closest papers by meaning
- RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension (AAAI 2025 · similarity 0.93)
- Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks (ICLR 2026 · similarity 0.90)
- ScanFormer: Referring Expression Comprehension by Iteratively Scanning (CVPR 2024 · similarity 0.90)
- DiffusionREC: Diffusion Model with Adaptive Condition for Referring Expression Comprehension (AAAI 2025 · similarity 0.90)
- Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point (AAAI 2024 · similarity 0.89)
- A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era (NeurIPS 2024 · similarity 0.89)
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.