Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Dewen, Hussain, Tahir, An, Wangpeng, Shouno, Hayaru
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.21317
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918071217684480
author Zhang, Dewen
Hussain, Tahir
An, Wangpeng
Shouno, Hayaru
author_facet Zhang, Dewen
Hussain, Tahir
An, Wangpeng
Shouno, Hayaru
contents Current vision-language models (VLMs) are well-adapted for general visual understanding tasks. However, they perform inadequately when handling complex visual tasks related to human poses and actions due to the lack of specialized vision-language instruction-following data. We introduce a method for generating such data by integrating human keypoints with traditional visual features such as captions and bounding boxes, enabling more precise understanding of human-centric scenes. Our approach constructs a dataset comprising 200,328 samples tailored to fine-tune models for human-centric tasks, focusing on three areas: conversation, detailed description, and complex reasoning. We establish an Extended Human Pose and Action Understanding Benchmark (E-HPAUB) to assess model performance on human pose and action understanding. We fine-tune the LLaVA-1.5-7B model using this dataset and evaluate our resulting LLaVA-Pose model on the benchmark, achieving significant improvements. Experimental results show an overall improvement of 33.2% compared to the original LLaVA-1.5-7B model. These findings highlight the effectiveness of keypoint-integrated data in enhancing multimodal models for human-centric visual understanding. Code is available at https://github.com/Ody-trek/LLaVA-Pose.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21317
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning
Zhang, Dewen
Hussain, Tahir
An, Wangpeng
Shouno, Hayaru
Computer Vision and Pattern Recognition
Current vision-language models (VLMs) are well-adapted for general visual understanding tasks. However, they perform inadequately when handling complex visual tasks related to human poses and actions due to the lack of specialized vision-language instruction-following data. We introduce a method for generating such data by integrating human keypoints with traditional visual features such as captions and bounding boxes, enabling more precise understanding of human-centric scenes. Our approach constructs a dataset comprising 200,328 samples tailored to fine-tune models for human-centric tasks, focusing on three areas: conversation, detailed description, and complex reasoning. We establish an Extended Human Pose and Action Understanding Benchmark (E-HPAUB) to assess model performance on human pose and action understanding. We fine-tune the LLaVA-1.5-7B model using this dataset and evaluate our resulting LLaVA-Pose model on the benchmark, achieving significant improvements. Experimental results show an overall improvement of 33.2% compared to the original LLaVA-1.5-7B model. These findings highlight the effectiveness of keypoint-integrated data in enhancing multimodal models for human-centric visual understanding. Code is available at https://github.com/Ody-trek/LLaVA-Pose.
title LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.21317