AI Paper Atlas

Research map / 3D vision / Human pose estimation

GeoX-Bench: Benchmarking Cross-View Geo-Localization and Pose Estimation Capabilities of Large Multimodal Models

Yushuo Zheng, Jiangyong Ying, Huiyu Duan, Chunyi Li, Zicheng Zhang, Jing Liu, Xiaohong Liu, Guangtao Zhai

AAAI 2026 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 6 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
LoRA instruction tuning on GeoX-BenchInternVL3-8B · Pose estimation (fixed)accuracy: 25.36 -> 55.36Improved
LoRA instruction tuning on GeoX-BenchInternVL3-8B · Average (7 tasks)accuracy: 40.08 -> 71.35Improved
LoRA instruction tuning on GeoX-BenchInternVL2-8B · Pose estimation (fixed)accuracy: 26.27 -> 25.00No clear effect
LoRA instruction tuning on GeoX-BenchQwen2.5VL-7B · Average (7 tasks)accuracy: 38.56 -> 67.38Improved
LoRA instruction tuning on GeoX-BenchQwen2VL-7B · Average (7 tasks)accuracy: 36.03 -> 68.96Improved
scale model up (2B to 72B)LMMs · Option biasnormalized entropy: 0.4412 (Qwen2VL-2B) -> 0.8216 (Qwen2VL-72B)Improved
scale beyond about 32B parameterspretrained LMMs · Average (7 tasks)accuracy: 43.76 (Qwen2.5VL-32B) -> 48.30 (72B)No clear effect
scale model up on pose estimationpretrained LMMs · Pose estimationaccuracy: no open model above 30%No clear effect

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