Production infrastructure for machine learning at scale

HDLBits website practices & solutions

MOT using deepsort and yolov3 with pytorch

A simple but efficient transformer model for video action recognition

Hiera: A fast, powerful, and simple hierarchical vision transformer.

official implementation of the spatial-temporal attention neural network (STANet) for remote sensing image change detection

Official PyTorch implementation of ACTION-Net: Multipath Excitation for Action Recognition (CVPR'21)

规范化管理labelme数据集并生成coco数据集

2023年，最新音视频学习资料整理，项目（调试可用），ffmpeg命令手册，文章，编解码论文，视频讲解，面试题全套资料

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

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…

BasicTAD: an Astounding RGB-Only Baselinefor Temporal Action Detection

[ICCV2023] UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer

computer vision projects | 计算机视觉相关好玩的AI项目（Python、C++、embedded system）

This code is used to view and use the data of C-MHAD

Some scripts on generating homemade AVA format datasets

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

The second generation of YOWO action detector.

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

via->yolo, yolo->via

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

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

中文独立博客列表

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。

AI绘画资料合集（包含国内外可使用平台、使用教程、参数教程、部署教程、业界新闻等等） Stable diffusion、AnimateDiff、Stable Cascade 、Stable SDXL Turbo