gmayday1997

ETSS-08-Data. Traffic Surveillance Data Generation capable of producing various environment record on road.

freeway-anomaly-data. Jupyter Notebook

VideoHV-Agent. Official implementation of "Think, Then Verify: A Hypothesis–Verification Multi-Agent Framework for Long Video Understanding(CVPR'2026)"

UnicomBenchmark. UnicomAI Large Model Benchmark

OpenLane-V2. [NeurIPS 2023 Track Datasets and Benchmarks] OpenLane-V2: The First Perception and Reasoning Benchmark for Road Driving

CodexGuide. CodexGuide：面向全球初学者、创作者、开发者与团队的 Codex 实践指南

AI-Research-SKILLs. Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

viewdelta-scd. Python

RELO. Code and models for RELO

Ultra-Fast-Lane-Detection-v2. Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification (TPAMI 2022)

VINE-main. [CVPR Finding 2026] Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation

cowtracker. CoWTracker: Tracking by Warping instead of Correlation

DFormer. [CVPR 2025] DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation & [ICLR 2024] DFormer & [NeuriPS 2025] OmniSegmentor

SFMFusion. 【TIP 2025】Spatial-Frequency Enhanced Mamba for Multi-Modal Image Fusion

TraffiX-Qwen. [ICML 2025] Official implementation of TraffiX-Qwen model introduced in TUMTraf VideoQA benchmark for roadside traffic video understanding.

RoScenes. [ECCV 2024] RoScenes: A large-scale multi-view 3d dataset for roadside perception

flowmap. [3DV 2025] Code for "FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent" by Cameron Smith*, David Charatan*, Ayush Tewari, and Vincent Sitzmann

tapnet. Tracking Any Point (TAP)

Detection-of-Traffic-Anomaly. This is the repo for our Detection of Traffic Anomaly (DoTA) dataset.

road-dataset. Download and pre-processing of ROAD dataset

Ubiquitous-Traffic-Eye. The dataset includes quantities vehicle trajectories at several sites. The dataset is extracted from aerial videos. Human work is used to ensure accuracy.

spill-detection. 核心功能为抛洒物检测。

NHA12D-Crack-Detection-Dataset-and-Comparison-Study.

easy-dataset. A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

label-studio. Label Studio is a multi-type data labeling and annotation tool with standardized output format

LOTVS-DADA. Driver Attention Prediction in Accidental Scenarios

cross_modal_adaptation. Cross-modal few-shot adaptation with CLIP

HVI-CIDNet. [CVPR2025 && NTIRE2025] HVI: A New Color Space for Low-light Image Enhancement (Official Implementation)

Valuate-and-Enhance-Multimodal-Cooperation. The repo for "Enhancing Multi-modal Cooperation via Sample-level Modality Valuation", CVPR 2024

ChangeDiff. (AAAI-2025) ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model

DungeonRush. 👾🐍 A opensource game inspired by Snake, written in pure C with SDL

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

ELD. Physics-based Noise Modeling for Extreme Low-light Photography (CVPR 2020 Oral & TPAMI 2021)

ASAPNet. Python

SFNet. [ICLR 2023] Selective Frequency Network for Image Restoration

highD-dataset. MATLAB

awesome-low-light-image-enhancement. This is a resouce list for low light image enhancement

coord-conv-pytorch. An intriguing failing of convolutional neural networks and the CoordConv solution in PyTorch

VeRidataset. This is the project page for veri dataset which is a large scale image dataset for vehicle re-identification in urban traffic surveillance.

LLFlow. [AAAI 2022] The code release of paper "AAAI Low-Light Image Enhancement with Normalizing Flow"

DNF. [CVPR 2023 Highlight] DNF: Decouple and Feedback Network for Seeing in the Dark

retinanet_traffic_3D. Implementation for paper: "Detection of 3D bounding boxes of vehicles using perspective transformation for accurate speed measurement"

HRank. Pytorch implementation of our paper accepted by CVPR 2020 (Oral) -- HRank: Filter Pruning using High-Rank Feature Map

awesome-pruning.

filter-pruning-geometric-median. Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (CVPR 2019 Oral)

anylabeling. Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!

SNR-Aware-Low-Light-Enhance. This is the official implementation for the paper "SNR-aware low-light image enhancement" in CVPR2022

FourLLIE. This is the official pytorch implementation of "FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Information" (ACM MM 2023)

RetinexNet_PyTorch. Unofficial PyTorch code for the paper - Deep Retinex Decomposition for Low-Light Enhancement, BMVC'18

Lighting-the-Darkness-in-the-Deep-Learning-Era-Open.

GSAD. [NeurIPS 2023] Global Structure-Aware Diffusion Process for Low-Light Image Enhancement

FcaNet. FcaNet: Frequency Channel Attention Networks

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

ExposureDiffusion. [ICCV 2023] ExposureDiffusion: Learning to Expose for Low-light Image Enhancement

FastSAM. Fast Segment Anything

ABODA. Abandoned Object Dataset

UnSniffer. [CVPR 2023] Official Pytorch code for Unknown Sniffer for Object Detection: Don’t Turn a Blind Eye to Unknown Objects

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

torchstat. Model analyzer in PyTorch

typst. A markup-based typesetting system that is powerful and easy to learn.

prompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

PyMuPDF. PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

ChatGLM-6B. ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

OpenSeeD. [ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"

TaskMatrix. Python

SegFormer. Official PyTorch implementation of SegFormer

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

prototypical-networks. Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"

opendet2. Official code of the paper "Expanding Low-Density Latent Regions for Open-Set Object Detection" (CVPR 2022)

cctv. Python

Active-Passive-Losses. [ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels

AirDet. Full conference version of AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration

PCAA. Code for "Partial Class Activation Attention for Semantic Segmentation" [CVPR2022]

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

The-Art-of-Linear-Algebra. Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"

mmfewshot. OpenMMLab FewShot Learning Toolbox and Benchmark

Yolov7_StrongSORT_OSNet. Real-time multi-object tracker using YOLOv7 and StrongSORT with OSNet

align_uniform. Open source code for paper "Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere" ICML 2020

tet. Implementation of Tracking Every Thing in the Wild, ECCV 2022

External-Attention-pytorch. 🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

Cam2BEV. TensorFlow Implementation for Computing a Semantically Segmented Bird's Eye View (BEV) Image Given the Images of Multiple Vehicle-Mounted Cameras.

SADE-AgnosticLT. This repository is the official Pytorch implementation of Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition (NeurIPS 2022).

hsnet. Official PyTorch Implementation of Hypercorrelation Squeeze for Few-Shot Segmentation, ICCV 2021

argoverse-api. Official GitHub repository for Argoverse dataset

SummaryOfLoanSuspension. 全国各省市停贷通知汇总

brokenaxes. Create matplotlib plots with broken axes

DeepBDC. The Pytorch code of "Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification", CVPR 2022 (Oral).

camodocal. CamOdoCal: Automatic Intrinsic and Extrinsic Calibration of a Rig with Multiple Generic Cameras and Odometry

darktable. darktable is an open source photography workflow application and raw developer

labelGo. Semi-automatic annotation tool for object detection.

Ultra-Fast-Lane-Detection. Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

birds-eye-view. Obtain bird's eye view of a scene from a single input image

ONNX-Runtime-Inference. ONNX Runtime Inference C++ Example

LTR-weight-balancing. CVPR 2022 - official implementation for "Long-Tailed Recognition via Weight Balancing" https://arxiv.org/abs/2203.14197

onnx. Open standard for machine learning interoperability

onnxruntime. ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

opencv. Open Source Computer Vision Library

libevent. Event notification library

muduo. Event-driven network library for multi-threaded Linux server in C++11

FEAT. The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"

MAK. [NeurIPS 2021] “Improving Contrastive Learning on Imbalanced Data via Open-World Sampling”, Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang

Awesome-LongTailed-Learning. A codebase and a curated list of awesome deep long-tailed learning (TPAMI 2023).

2021-AAAI-CC. Code for the paper "Contrastive Clustering" (AAAI 2021)

FRN. (CVPR 2021) Few-Shot Classification with Feature Map Reconstruction Networks

RIDE-LongTailRecognition. [ICLR 2021 Spotlight] Code release for "Long-tailed Recognition by Routing Diverse Distribution-Aware Experts."

awesome-multiple-object-tracking. Resources for Multiple Object Tracking (MOT)

HowToCook. Programmer's guide about how to cook at home.

CFL. Python

Long-Tailed-Recognition.pytorch. [NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation (LVIS). It is also a PyTorch implementation of the NeurIPS 2020 paper 'Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect'.

annotated_latex_equations. Examples of how to create colorful, annotated equations in Latex using Tikz.

classifier-balancing. This repository contains code for the paper "Decoupling Representation and Classifier for Long-Tailed Recognition", published at ICLR 2020

MMD_Loss.Pytorch. A pytorch implementation of Maximum Mean Discrepancies(MMD) loss

PFENet. PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation (TPAMI).

LaneNet. Pytorch implementation of "Towards end-to-end lane detection: an instance segmentation approach"

Few-Shot-Semantic-Segmentation-Papers. Few Shot Semantic Segmentation Papers

camera_calibration. Accurate geometric camera calibration with generic camera models

osr_closed_set_all_you_need. Official repo for our ICLR 22 Oral paper: "Open-Set Recognition: a Good Closed-Set Classifier is All You Need?"

dynamic-cdfsl. Pytorch codes for NeurIPS 2021 paper titled "Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data".

Awesome-of-Long-Tailed-Recognition. A curated list of long-tailed recognition resources.

awesome-papers-fewshot. Collection for Few-shot Learning

PMMs. Prototype Mixture Models for Few-shot Semantic Segmentation

pytorch-lanenet. LaneNet implementation in PyTorch

self-driving-ish_computer_vision_system. This project generates images you've probably seen in autonomous driving demo. Object Detection, Lane Detection, Road Segmentation, Depth Estimation using TensorRT

CloserLookFewShot. source code to ICLR'19, 'A Closer Look at Few-shot Classification'

ml4a-ofx. A collection of openFrameworks apps for working with machine learning

PT-MAP. Code for 'Leveraging the Feature Distribution in Transfer-based Few-Shot Learning'

BalancedMetaSoftmax-Classification. [NeurIPS 2020] Balanced Meta-Softmax for Long-Tailed Visual Recognition

Focal-Transformer. [NeurIPS 2021 Spotlight] Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"

nsfc. 国家自然科学基金查询

pcan. Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight

sphereface. Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.

darknet-yolo-segmentation. This project is based on darknet to get image segmentation

few-shot-classification-leaderboard. Leaderboards for few-shot image classification on miniImageNet, tieredImageNet, FC100, and CIFAR-FS.

University1652-Baseline. ACM Multimedia2020 University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization :helicopter: annotates 1652 buildings in 72 universities around the world.

yacs. YACS -- Yet Another Configuration System

CarCrashDataset. [ACM MM 2020] CCD dataset for traffic accident anticipation.

hf2vad. Python

LibFewShot. [TPAMI 2023] LibFewShot: A Comprehensive Library for Few-shot Learning.

deep-hough-transform. Jittor and Pytorch code for paper "Deep Hough Transform for Semantic Line Detection" (ECCV 2020, PAMI 2021)

Codes-for-Lane-Detection. Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)

pytorch-metric-learning. The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

incubator-mxnet. Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

BrnoCompSpeed. Code for BrnoCompSpeed dataset

DeepCalib. DeepCalib: A Deep Learning Approach for Automatic Intrinsic Calibration of Wide Field-of-View Cameras

DeepEMD. Code for paper "DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover's Distance and Structured Classifiers", CVPR2020

pytorch-cpp. C++ Implementation of PyTorch Tutorials for Everyone

PaddleOCR2Pytorch. PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)

OpenLongTailRecognition-OLTR. Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)

OWOD. (CVPR 2021 Oral) Open World Object Detection

Siamese-Networks-for-One-Shot-Learning. Implementation of Siamese Neural Networks for One-shot Image Recognition

TransTrack. Multiple Object Tracking with Transformer

CalibrationWizard. [ICCV'19] Calibration Wizard: A Guidance System for Camera Calibration Based on Modelling Geometric and Corner Uncertainty

DCRNN. Implementation of Diffusion Convolutional Recurrent Neural Network in Tensorflow

GMAN. GMAN: A Graph Multi-Attention Network for Traffic Prediction (GMAN, https://fanxlxmu.github.io/publication/aaai2020/) was accepted by AAAI-2020.

Cal_PnP. C++ implementation of semi-automatic camera calibration based on Perspective-n-Point (PnP)

pytorchOCR. 基于pytorch的ocr算法库，包括 psenet, pan, dbnet, sast , crnn

Research. novel deep learning research works with PaddlePaddle

pixel-level-contrastive-learning. Implementation of Pixel-level Contrastive Learning, proposed in the paper "Propagate Yourself", in Pytorch

RoadDamageDetector. Jupyter Notebook

Attention_ocr.pytorch. This repository implements the the encoder and decoder model with attention model for OCR

lambda-networks. Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

SupContrast. PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

yolo_segmentation. image (semantic segmentation) instance segmentation by darknet or yolo

LaneDetection_End2End. End-to-end Lane Detection for Self-Driving Cars (ICCV 2019 Workshop)

DifferentiableBinarization. DB (Real-time Scene Text Detection with Differentiable Binarization) implementation in Keras and Tensorflow

Lets_OCR. A repository for OCR, which inlcudes some classical OCR algorithms Pytorch implementation such as CTPN, EAST and CRNN.

VG_AlexeyAB_darknet. A forked AlexeyAB Darknet repo with extra convenient functions.

PytorchOCR. 基于Pytorch的OCR工具库，支持常用的文字检测和识别算法

VisDrone-Dataset. The dataset for drone based detection and tracking is released, including both image/video, and annotations.

AICIty-reID-2020. :red_car: The 1st Place Submission to AICity Challenge 2020 re-id track (Baidu-UTS submission)

RoadCrackDetection. Python

CCPD. [ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition

alibabacloud-quantization-networks. alibabacloud-quantization-networks

VIBE. VIBE Background Subtractior

caffe_ocr. 主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构

Towards-Realtime-MOT. Joint Detection and Embedding for fast multi-object tracking

bhtsne. Barnes-Hut t-SNE

CrackForest-dataset.

Paddle-Lite. PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）

PaddleOCR. Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

chineseocr_lite. 超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

CTPN. Detecting Text in Natural Image with Connectionist Text Proposal Network (ECCV'16)

darknet-ocr. darknet text detect and darknet cnn ocr

PL-ZSD_Release. This repository provides training and evaluation code for paper titled "Polar Loss for Zero-Shot Object Detection." (Arxiv version) and "Improved Visual-Semantic Alignment for Zero-Shot Object Detection" (accepted in AAAI 2020)

Paddle. PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

FairMOT. [IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

introRL. Intro to Reinforcement Learning (强化学习纲要）

CenterTrack. Simultaneous object detection and tracking using center points.

One-Shot-Learning-with-Siamese-Networks. Implementation of One Shot Learning using Convolutional Siamese Networks on Omniglot Dataset

Awesome-Multi-Camera-Network. Multi-camera Network research resources

BBN. The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

SimCLR. PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

Vehicle-Distance-Detection. Using Perspective Transform to leverage bird's eye view (BEV) to estimate distance between objects.

few-shot-meta-baseline. Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning, in ICCV 2021

vehicle-dsm. Vehicle detection and speed measurement system

Traffic-Net. A dataset of traffic, fire and accident images for training deep learning models.

ZSD_Release. This repository provides evaluation code for paper titled "Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts."

Deeperlab-pytorch. Segmentation realize Deeperlab only segmentation part

CorrFlow. Self-supervised Learning for Video Correspondence Flow (BMVC 2019)