AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs Article Swipe

MAKE IMPACT

Yi‐Ting Shen , Sungmin Eum , Doheon Lee , Rohit Shete , Chiao-Yi Wang , Heesung Kwon , Shuvra S. Bhattacharyya · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2503.22884

Composed pose retrieval (CPR) enables users to search for human poses by specifying a reference pose and a transition description, but progress in this field is hindered by the scarcity and inconsistency of annotated pose transitions. Existing CPR datasets rely on costly human annotations or heuristic-based rule generation, both of which limit scalability and diversity. In this work, we introduce AutoComPose, the first framework that leverages multimodal large language models (MLLMs) to automatically generate rich and structured pose transition descriptions. Our method enhances annotation quality by structuring transitions into fine-grained body part movements and introducing mirrored/swapped variations, while a cyclic consistency constraint ensures logical coherence between forward and reverse transitions. To advance CPR research, we construct and release two dedicated benchmarks, AIST-CPR and PoseFixCPR, supplementing prior datasets with enhanced attributes. Extensive experiments demonstrate that training retrieval models with AutoComPose yields superior performance over human-annotated and heuristic-based methods, significantly reducing annotation costs while improving retrieval quality. Our work pioneers the automatic annotation of pose transitions, establishing a scalable foundation for future CPR research.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2503.22884

PDF

https://arxiv.org/pdf/2503.22884

OA Status

green

OpenAlex ID

https://openalex.org/W4414990877

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4414990877

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2503.22884

Digital Object Identifier

Title

AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-03-28

Full publication date if available

Authors

Yi‐Ting Shen, Sungmin Eum, Doheon Lee, Rohit Shete, Chiao-Yi Wang, Heesung Kwon, Shuvra S. Bhattacharyya

List of authors in order

Landing page

https://arxiv.org/abs/2503.22884

Publisher landing page

PDF URL

https://arxiv.org/pdf/2503.22884

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2503.22884

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload