Code for the SPIE 2025 paper: A Study on the Performance of U-Net Modifications in Retroperitoneal Tumor Segmentation

Large Language Models: In this repository Language models are introduced covering both theoretical and practical aspects.

Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-t…

Transformers and related deep network architectures are summarized and implemented here.

A paper list of some recent Transformer-based CV works.

🛠 A lite C++ toolkit of 100+ Awesome AI models, support ORT, MNN, NCNN, TNN and TensorRT. 🎉🎉

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

EvoPose2D is a two-stage human pose estimation model that was designed using neuroevolution. It achieves state-of-the-art accuracy on COCO.

CNN-based fast source device identification

Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.

Activity Recognition from 2D pose using an LSTM RNN

Implementation of "Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision" in PyTorch.

Official implementation of Adabins: Depth Estimation using adaptive bins

Cork/Face Presentation Attack Detection

Convert video to 3D pose in one-key.

静默活体检测（Silent-Face-Anti-Spoofing）

[ECCV2020] A Large-Scale Face Anti-Spoofing Dataset

A skeleton-based real-time online action recognition project, classifying and recognizing base on framewise joints, which can be used for safety surveilence.

Keras implementation of 3d-pose-baseline

realtime 3D pose estimation for wild videos， embed 2d keypoints detector like hrnet alphapose and openpose

2D and 3D pose estimation

VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera

A Graph Attention Spatio-temporal Convolutional Networks for 3D Human Pose Estimation in Video (GAST-Net)

Online 3D skeleton-based action recognition with a single RGB camera

We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocula…

Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network (ECCV 2018)' paper

This project reimplements from scratch the OpenPose paper (Cao et al,2018), Using Tensorflow 2.1 and optional TPU powered training.