使用Qt6开发的本地音视频播放器，主要功能有视频播放/暂停、音量调节、进度条拖动、播放列表、上一个下一个等。

高性能RTSP推流服务器，支持在Linux和Windows系统。实现RTSP协议的核心信令交互（OPTIONS、DESCRIBE、SETUP、PLAY、TEARDOWN），并支持H.264和AAC文件的实时推流。通过 RTP 封装NALU和ADTS单元，实现音视频同步传输。实现多种I/O模型（select、poll、epoll），并可以使用TCP和UDP传输协议，适用于视频点播应用场景。

本项目是一个基于 RTSP协议的流媒体服务器。该服务器能够接收客户端的请求，处理不同的 RTSP 方法（如 OPTIONS、DESCRIBE、SETUP、PLAY 等），并通过 RTP（实时传输协议）发送视频和音频流。服务器主要的功能包括处理流媒体控制请求并将视频和音频数据通过 RTP 封装后推流发送给客户端。

WebRTC/RTSP/RTMP/HTTP/HLS/HTTP-FLV/WebSocket-FLV/HTTP-TS/HTTP-fMP4/WebSocket-TS/WebSocket-fMP4/GB28181/SRT server and client framework based on C++11

[ECCV 2020] Codes and MultiviewX dataset for "Multiview Detection with Feature Perspective Transformation".

Applying Perspective transformations to 2d images.

A Library for Advanced Deep Time Series Models.

The official PyTorch implementation of L2CS-Net for gaze estimation and tracking

Gaze estimation using MPIIGaze and MPIIFaceGaze

Deformable Convolutional Networks v2 with Pytorch

Python GUI program to do Perspective Transformation using Mouse Click to map the 4 points coordinates.

This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

This is an official implementation of our CVPR 2021 paper "Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression" (https://arxiv.org/abs/2104.02300)