---
pipeline_tag: keypoint-detection
license: agpl-3.0
---
## Components
The models used to create the multi-task model. Please refer to there individual pages for more information.

Models in this repository:
- YOLOv11: https://github.com/ultralytics/ultralytics
  - yolov11n.pt
- yolo-face: https://github.com/akanametov/yolo-face
  - yolov11n-face.pt
- AdaFace: https://github.com/mk-minchul/AdaFace/tree/master
  - adaface_ir50_ms1mv2.ckpt

Additionally, Other models are used in the multi-task model:
- ViTPose: https://github.com/ViTAE-Transformer/ViTPose
  - We use HuggingFace Transformers to load the model
- ResNet: https://arxiv.org/abs/1512.03385, https://pytorch.org/vision/main/models/resnet.html
  - We use TorchVision to load the model


Please see the following link for the full code repository: 

https://github.com/Person-Recognition-for-Pose-Estimation/Person-Recognition-for-Pose-Estimation

Licensed under the AGPL-3.0 license to respect the YOLO license. 
Please look at the individual repositories for more information.