Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Dewen, Hussain, Tahir, An, Wangpeng, Shouno, Hayaru
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.09139
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918090439131136
author Zhang, Dewen
Hussain, Tahir
An, Wangpeng
Shouno, Hayaru
author_facet Zhang, Dewen
Hussain, Tahir
An, Wangpeng
Shouno, Hayaru
contents Human pose estimation traditionally relies on architectures that encode keypoint priors, limiting their generalization to novel poses or unseen keypoints. Recent language-guided approaches like LocLLM reformulate keypoint localization as a vision-language task, enabling zero-shot generalization through textual descriptions. However, LocLLM's linear projector fails to capture complex spatial-textual interactions critical for high-precision localization. To address this, we propose PoseLLM, the first Large Language Model (LLM)-based pose estimation framework that replaces the linear projector with a nonlinear MLP vision-language connector. This lightweight two-layer MLP with GELU activation enables hierarchical cross-modal feature transformation, enhancing the fusion of visual patches and textual keypoint descriptions. Trained exclusively on COCO data, PoseLLM achieves 77.8 AP on the COCO validation set, outperforming LocLLM by +0.4 AP, while maintaining strong zero-shot generalization on Human-Art and MPII. Our work demonstrates that a simple yet powerful nonlinear connector significantly boosts localization accuracy without sacrificing generalization, advancing the state-of-the-art in language-guided pose estimation. Code is available at https://github.com/Ody-trek/PoseLLM.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09139
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment
Zhang, Dewen
Hussain, Tahir
An, Wangpeng
Shouno, Hayaru
Computer Vision and Pattern Recognition
Human pose estimation traditionally relies on architectures that encode keypoint priors, limiting their generalization to novel poses or unseen keypoints. Recent language-guided approaches like LocLLM reformulate keypoint localization as a vision-language task, enabling zero-shot generalization through textual descriptions. However, LocLLM's linear projector fails to capture complex spatial-textual interactions critical for high-precision localization. To address this, we propose PoseLLM, the first Large Language Model (LLM)-based pose estimation framework that replaces the linear projector with a nonlinear MLP vision-language connector. This lightweight two-layer MLP with GELU activation enables hierarchical cross-modal feature transformation, enhancing the fusion of visual patches and textual keypoint descriptions. Trained exclusively on COCO data, PoseLLM achieves 77.8 AP on the COCO validation set, outperforming LocLLM by +0.4 AP, while maintaining strong zero-shot generalization on Human-Art and MPII. Our work demonstrates that a simple yet powerful nonlinear connector significantly boosts localization accuracy without sacrificing generalization, advancing the state-of-the-art in language-guided pose estimation. Code is available at https://github.com/Ody-trek/PoseLLM.
title PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.09139