Discover @layumi Open Source projects

Zhedong Zheng (@layumi)

layumi

Stars
8,329
Global Rank 2,799 (Top 0.1 %)
Followers 1,933
Following 603
Registered over 10 years ago
Most used languages

Python
46.7 %

HTML
15.6 %

MATLAB
13.3 %

Cuda 13.3 %

C
4.4 %

C++
2.2 %

M 2.2 %

CSS
2.2 %
Location 🇲🇴 Macao
Country Total Rank 27
Country Ranking

Cuda 1

HTML
1

M 1

MATLAB
1

Python
1

C
2

CSS
10

C++
14

Person_reID_baseline_pytorch

⛹️ Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

Vehicle_reID-Collection

🚗 the collection of vehicle re-ID papers, datasets. 🚗

University1652-Baseline

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

AICIty-reID-2020

🚗 The 1st Place Submission to AICity Challenge 2020 re-id track (Baidu-UTS submission)

Seg-Uncertainty

IJCAI2020 & IJCV2021 🌇 Unsupervised Scene Adaptation with Memory Regularization in vivo

Person-reID_GAN

ICCV2017 Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro

Image-Text-Embedding

TOMM2020 Dual-Path Convolutional Image-Text Embedding 🐾 https://arxiv.org/abs/1711.05535

2016_person_re-ID

TOMM2017 A Discriminatively Learned CNN Embedding for Person Re-identification

person-reid-3d

TNNLS'22 🗽 Parameter-Efficient Person Re-identification in the 3D Space 🗽

Pedestrian_Alignment

TCSVT2018 Pedestrian Alignment Network for Large-scale Person Re-identification

Person-reID-triplet-loss

Person re-ID baseline with triplet loss

2015_Face_Detection

CVPR2015 Cascade CNNs for Face Detection

Person-reID-verification

🐨 (pytorch version) TOMM2017 A Discriminatively Learned CNN Embedding for Person Re-identification 🐨

2016_super_resolution

ICCV2015 Image Super-Resolution Using Deep Convolutional Networks

Awesome-Fools

💀 A collection of methods to fool the deep neural network 💀

3D-Magic-Mirror

👗3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective👗 Single-View 3D Reconstruction

U_turn

IJCV22 🙈 Attack your retrieval model via Query! They are not robust as you expected! 🙉

AdaBoost_Seg

TIP2022 Adaptive Boosting (AdaBoost) for Domain Adaptation ? 🤷‍♀️ Why not ! 🙆‍♀️

visualize_matconvnet

A simple code to visualize net for matconvnet.

2016_GAN_Matlab

Generative Adversarial Nets for Matlab

2016_Artist_Style

Using CNN to create 'famous painting' with Matlab code

DukeMTMC-reID_baseline

DukeMTMC-reID_baseline (Matlab)

UTS-Person-reID-Practical

UTS Person-reID Practical By Zhedong Zheng

HQ-Market

Market-1501 dataset with super-resolution quality

Image-Retrieval-by-Finetuning-CNN

Code for project

Awesome-Text2Motion-Generation

Awesome-Text2Motion-Generation

ACMMM2023Workshop

UAVM @ ACM MM2023 Workshop on UAVs in Multimedia: Capturing the World from a New Perspective

NLP-AICity2021

The 1st Place Submission to AICity Track5 - Natural Language-based Vehicle Retrieval.

UAVM2023

ACM MM Workshop on UAVs in Multimedia: Capturing the World from a New Perspective (UAVM 2023)

Person_reID_baseline_matconvnet

Matconvnet implement of Person re-identification baseline. We arrived Rank@1=87.74% mAP=69.46% only with softmax loss.

matlab_email_demo

a easy solution for baby sitting program!!! (MATLAB)

ICME2022SS

ICME2022 Special Session “Beyond Accuracy: Responsible, Responsive, and Robust Multimedia Retrieval ”

To-Academic-Newcomers

DCGAN-pytorch

Pytorch implement of DCGAN and LSGAN

University1652-triplet-loss

triplet loss with hard negative / soft margin for the University-1652 dataset.

2016_Class_Activation_Mapping

semantic segmentation in MATLAB

Robust-GPUs

layumi.github.io

UTS Group Seminar http://www.zdzheng.xyz

market1501_body_point

Cifar10-Adaboost

2016_Center_Loss

Matlab_ECCV16_Center_Loss

google_scholar_scrapy

extract data from google scholar

Oxford-Paris-Attack

🙈 We added our attacking method ODFA (https://arxiv.org/abs/1809.02681). The performance drops from 88.2% to 2.24% on Oxford. 🙉

visualize_face_detection_net

SOTA-semi

Matlab_TripletLoss

Matlab_TripletLoss

Batch-Normal-For-Caffe

Extend batch normalization layer for caffe

pytorch-mnist

Awesome-Sign-Language

awesome list for sign language

2015_speech

word audio recognition

layumi

pkl2mat

a tool for transfer pkl file to mat file

ACMMM2024Workshop-UAV

ComputerVisionAwardPapers

2016_FlowNet

Zhedong-Zheng-blog

zhedong zheng's blog

2016_Video_Stabilization

A project @Fudan for 2016 Digital Image Processing

empty

Workshop-Proposal-DDL

WordNet_Matlab

a simple api for matlab to search semantic synonym

MORE2024

Multimedia Object Re-identification Workshop (MORE) @ ICMR2024