High performance self-hosted photo and video management solution.

Official implementation of "VideoMaMa: Mask-Guided Video Matting via Generative Prior"

这是一款基于FunASR实现的说话人分离的GUI程序

Implementation of "TrackFormer: Multi-Object Tracking with Transformers”. [Conference on Computer Vision and Pattern Recognition (CVPR), 2022]

Official pytorch implementation for "Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement"

MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator

The official repository of the paper "RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis"

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

This repository provides optical character detection and recognition solution optimized on Nvidia devices.

Torchreid: Deep learning person re-identification in PyTorch.

Resources for Multiple Object Tracking (MOT)

Yolov5 deepsort inference，使用YOLOv5+Deepsort实现车辆行人追踪和计数，代码封装成一个Detector类，更容易嵌入到自己的项目中

[CVPR'2025] URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration

Open-Source Frontier Voice AI

Tracking ball in volleyball using YOLO

Volleyball tracking - VballNet is a specialized deep learning framework designed for volleyball tracking, built upon the foundation of TrackNetV4. This repository includes two primary models, Vball…

Fast Volleyball Tracking Inference: Real-time volleyball ball detection and tracking at 100 FPS on CPU (Intel i5-10400F). Powered by an optimized ONNX model, outputs ball coordinates to CSV, with o…

Open-source Monocular Python HawkEye for Tennis

Web App for VolleyVision

This project is designed to display how we can utilize deep learning methods for Sports Data Analytics.

Applying Deep Learning Approaches to Volleyball Data

Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".

This repository show how to train and predict in Windows system, and onnx runtime

A real-time implementation of Voice Activity Projection (VAP) is aimed at controlling behaviors of spoken dialogue systems, such as turn-taking.

Implementation of the KaliCalib paper

Computer vision project that maps a 2d basketball court and tracks players movement from video footage, in order to obtain a video containing each players movement on the court during a basketball …

[TPAMI 2025] MOWA: Multiple-in-One Image Warping Model

clash for windows汉化版. 提供clash for windows的汉化版, 汉化补丁及汉化版安装程序