Light

zoooo0820 / paddlevideo Goto Github PK

View Code? Open in Web Editor NEW

This project forked from paddlepaddle/paddlevideo

0.0 1.0 0.0 102.15 MB

基于模块化的设计，提供丰富的视频算法实现、产业级的视频算法优化与应用，包括安防、体育、互联网、媒体等行业的动作定位与识别、行为分析、智能封面、视频标注、视频打标签等，涵盖动作识别与视频分类、动作定位、动作检测、多模态文本视频检索等技术。

License: Apache License 2.0

Python 95.01% Shell 3.49% CMake 0.27% C++ 1.22%

paddlevideo's Introduction

English | 中文

PaddleVideo

近期更新

发布轻量化行为识别模型🌟PP-TSMv2🌟, Kinetics-400精度74.38%，25fps的10s视频cpu推理时间仅需433ms.
新增知识蒸馏功能.
发布各模型benchmark文档.
更新快速开始文档.
新增基于transformer的行为识别模型TokenShift.
新增基于骨骼点的行为识别模型2s-ACGN、CTR-GCN.

👀 🌟 《产业级视频技术与应用案例》系列课程回放链接: https://aistudio.baidu.com/aistudio/course/introduce/6742 🌟

💖 欢迎大家扫码入群讨论 💖

添加成功后回复【视频】加入交流群

简介

PaddleVideo是飞桨官方出品的视频模型开发套件，旨在帮助开发者更好的进行视频领域的学术研究和产业实践。

模型案例库

模型

模型库使用前请参考安装说明、使用指南。

行为识别方法
PP-TSM (PP series)	PP-TSN (PP series)	PP-TimeSformer (PP series)	TSN (2D’)	TSM (2D‘)
SlowFast (3D’)	TimeSformer (Transformer‘)	VideoSwin (Transformer’)	AttentionLSTM (RNN‘)	MoViNet (Lite‘)
基于骨骼点的动作识别方法
ST-GCN (GCN’)	AGCN (GCN‘)	CTR-GCN (GCN‘)
时序动作检测方法
BMN (One-stage‘)
视频时序分割
MS-TCN	ASRF
时空动作检测方法
SlowFast+Fast R-CNN
多模态
ActBERT (Learning‘)	T2VLAD (Retrieval‘)
视频目标分割
CFBI (Semi‘)	MA-Net (Supervised‘)
单目深度估计
ADDS (Unsupervised‘)

数据集

动作识别
Kinetics-400 (Homepage) (CVPR'2017)	UCF101 (Homepage) (CRCV-IR-12-01)	ActivityNet (Homepage) (CVPR'2015)	YouTube-8M (Homepage) (CVPR'2017)
动作定位
ActivityNet (Homepage) (CVPR'2015)
时空动作检测
AVA (Homepage) (CVPR'2018)
基于骨架的动作识别
NTURGB+D (Homepage) (IEEE CS'2016)	FSD (Homepage)
单目深度估计
Oxford-RobotCar (Homepage) (IJRR'2017)
文本视频检索
MSR-VTT (Homepage) (CVPR'2016)
文本视频预训练
HowTo100M (Homepage) (ICCV'2019)

应用案例

Applications	Descriptions
FootballAction	足球动作检测方案
BasketballAction	篮球动作检测方案
TableTennis	乒乓球动作识别方案
FigureSkating	花样滑冰动作识别方案
VideoTag	3000类大规模视频分类方案
MultimodalVideoTag	多模态视频分类方案
VideoQualityAssessment	视频质量评估方案
PP-Care	3DMRI医疗图像识别方案
EIVideo	视频交互式分割工具
Anti-UAV	无人机检测方案
AbnormalActionDetection	异常行为检测方案
PP-Human	行人分析场景动作识别方案

文档教程

赛事支持

许可证书

本项目的发布受Apache 2.0 license许可认证。

致谢

非常感谢 mohui37、zephyr-fun、voipchina 贡献相关代码

paddlevideo's People

Contributors

Watchers

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.