LLaVA-Pose: Keypoint-Integrated Instruction Tuning for Human Pose and Action Understanding

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...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Dewen Zhang, Tahir Hussain, Wangpeng An, Hayaru Shouno
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2025-08-01
coleção:	Sensors
Assuntos:	human pose and action understanding keypoint-integrated data generation instruction-following data vision–language models multimodal instruction tuning
Acesso em linha:	https://www.mdpi.com/1424-8220/25/16/5213
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!