EUVIMEDEUVIMED entdecken
Crossref

VLPose: Bridging the Domain Gap in Pose Estimation With Language-Vision Tuning

Jingyao Li, Pengguang Chen, Xuan Ju, Shu Liu, Hong Xu, Jiaya Jia

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-11 · 47 (11) · 10836-10847

DOI: 10.1109/tpami.2025.3594097 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-11. Verfasst von Jingyao Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: Research Grants Council through the Areas of Excellence scheme.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Thanks to advances in deep learning techniques, Human Pose Estimation (HPE) has achieved significant progress in natural scenarios. However, these models perform poorly in artificial scenarios such as painting and sculpture due to the domain gap, constraining the development of virtual reality and augmented reality. With the growth of model size, retraining the whole model on both natural and artificial data is computationally expensive and inefficient. Our research aims to bridge the domain gap between natural and artificial scenarios with efficient tuning strategies. Leveraging the potential of language models, we enhance the adaptability of traditional pose estimation models across diverse scenarios with a novel framework called VLPose. VLPose leverages the synergy between language and vision to extend the generalization and robustness of pose estimation models beyond the traditional domains. Our approach has demonstrated improvements of 2.26% and 3.74% on HumanArt and MSCOCO, respectively, compared to state-of-the-art tuning strategies.

Förderung

  • Research Grants Council through the Areas of Excellence scheme

Zitieren

APA

Li, J., Chen, P., Ju, X., Liu, S., Xu, H., & Jia, J. (2025). VLPose: Bridging the Domain Gap in Pose Estimation With Language-Vision Tuning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(11), 10836-10847. https://doi.org/10.1109/tpami.2025.3594097

Vancouver

Li J, Chen P, Ju X, Liu S, Xu H, Jia J. VLPose: Bridging the Domain Gap in Pose Estimation With Language-Vision Tuning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(11):10836-10847. doi:10.1109/tpami.2025.3594097

BibTeX
@article{Li2025,
  author = {Li, Jingyao and Chen, Pengguang and Ju, Xuan and Liu, Shu and Xu, Hong and Jia, Jiaya},
  title = {VLPose: Bridging the Domain Gap in Pose Estimation With Language-Vision Tuning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {11},
  pages = {10836--10847},
  doi = {10.1109/tpami.2025.3594097}
}
Kostenlos starten →