AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision

LING LI, Bowen Liu, Zinuo Zhan, Peng Jie, Jianhui Zhong, Kenglun Chang, Zhidong Deng

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
SV-CoT visual chain-of-thought reasoning on Qwen3-VL vs strongest open-source baselineQwen3-VL · EgoPoint-Ground EDG (Real-World)P@0.5: 0.701 -> 0.818Improved
SV-CoT vs strongest baselineQwen3-VL · EgoPoint-Ground EDG (Hybrid)P@0.5: 0.702 -> 0.756Improved
SV-CoT keeps accuracy at strict IoU 0.7 thresholdQwen3-VL · EgoPoint-Ground EDG (Real-World)P@0.7: 0.616 -> 0.727Improved
remove hand-pointing cue, language only (D-REC) vs both cues (ablation)Qwen3-VL-4B · EgoPoint-GroundP@0.5: 0.699 -> 0.684Hurt
remove language, pointing only (POG) vs both cues (ablation)Qwen3-VL-4B · EgoPoint-GroundP@0.5: 0.699 -> 0.612Hurt
SV-CoT in language-only setting vs best baselineQwen3-VL · EgoPoint-Ground D-RECP@0.5: 0.684 -> 0.750Improved
SV-CoT in pointing-only setting vs best baselineQwen3-VL · EgoPoint-Ground POGP@0.5: 0.612 -> 0.639Improved
real-world vs hybrid evaluation split for baselinesMLLM baselines · EgoPoint-Ground EDGP@0.5: Qwen3-VL-8B 0.676 -> 0.701; Qwen2.5-VL-3B 0.671 -> 0.632Mixed
MLLMs on deictic VQA vs humanLLaVA-OneVision-8B · EgoPoint-Ground D-VQA (Real-World)accuracy: 0.877 (human) vs 0.544Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy