[CVPR 2023] Official code release of our paper "BiFormer: Vision Transformer with Bi-Level Routing Attention"

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "Fast Vision Transformers with HiLo Attention"

Multiple Object Tracking with Transformer

Official PyTorch implementation of "Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking" (CVPR 2021).

(CVPR2024)RMT: Retentive Networks Meet Vision Transformer

Given TrackEval to write a little bit complicated, could not too friendly for beginners, so I want to a simple optimization makes it easier to evaluate custom data sets

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

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

Vision toolbox for video related tasks including action recognition, multi-object tracking.

OpenMMLab Detection Toolbox and Benchmark

Simple Online Realtime Tracking with a Deep Association Metric

45种类猫分类器

以猫种类的识别为例，使用Keras和卷积神经网络搭建图片分类系统

A neural network that classifies cat breeds from photos

《人工神经网络》课程的实验大作业，包括猫咪分类以及新闻标题分类任务

基于python+Keras+OpenCV利用CNN实现猫种类分类

基于tensorflow的猫咪分类

细粒度图像分类之十二猫分类，对比ResNet和ViT两者模型性能。