【A common used C++ DAG framework】 一个通用的、无三方依赖的、跨平台的、收录于awesome-cpp的、基于流图的并行计算框架。欢迎star & fork & 交流

Orbbec SDK v2 Open-Source Repo.

Shpe detection in 3D point clouds using RANSAC algorithm

Efficient RANSAC for Point-Cloud Shape Detection

A lightweight C++ implementation of YoloV8 running on NVIDIAs TensorRT engine

Integrate the DeepSeek API into popular softwares

Zero-DCE code and model

[CVPR 2022] This is the official code for the paper "Toward Fast, Flexible, and Robust Low-Light Image Enhancement".

TensorFlow Lite models for MIRNet for low-light image enhancement.

GPT4V-level open-source multi-modal model based on Llama3-8B

A full Python implementation for real car surround view system

A General-purpose Task-parallel Programming System using Modern C++

Student Classroom Behavior dataset

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video ta…

使用TensorRT部署SlowFast模型

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Custom ava dataset, Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions

real time face swap and one-click video deepfake with only a single image

download AVA dataset

使用onnxruntime部署YOWOv2视频动作检测，包含C++和Python两个版本的程序

The second generation of YOWO action detector.

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

Goodix GT7868Q Linux Driver

集成Dlib实现人脸识别模块，以及通过YOLOV5+DeepSort+SlowFast 实现多目标实时在线行为检测。并且开发功能对接接口，可以快速进行二次开发。

Yolov5+SlowFast: Realtime Action Detection Based on PytorchVideo