Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.

An unofficial implementation of ViTPose [Y. Xu et al., 2022]

VitPose without MMCV dependencies

Human pose estimation within one line

Easy inference tool for ViTPose using ONNX

Repository to evaluate Deep Learning Models for funscript generation

TopDown Pose Estimation on iOS

Simple pipeline using Yolov5 and ViTPose to annotate human pose in videos.

TopDown Pose Estimation on iOS and PureSwift.

An annotation tool that combines TCFormer and ViTPose as an ensemble setup for COCO Wholebody annotations.

專題產生訓練資料的儲存庫

A novel approach to detecting violence in videos by using hierarchical attention networks.