vitpose-base-simple is a simplified Vision Transformer baseline for human pose estimation, based on the ViTPose paper from the University of Sydney. It is available on Hugging Face with support for the Transformers library and includes model cards detailing training data and evaluation results. The model is designed for researchers and developers working on computer vision tasks involving human posture analysis.
Vitpose Base Simple sits in PulseGate's Other AI category. Accurately detecting human body keypoints and poses from images using transformer architectures. It is built as an open-source project for developers. The project is open source (Apache-2.0). It ships for the web and API.
usyd-community builds and maintains Vitpose Base Simple, and it first shipped in 2022. Development happens publicly on GitHub with 2.1k stars.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do