We extend the SPGAN (our prior work in CVPR2018) to an end-to-end version, named eSPGAN. https://arxiv.org/pdf/1811.10551.pdf

This is the repository for the implementation of PDA-Net for our ICCV 2019 paper

Reimplementation of Bag of Tricks and A Strong Baseline for Deep Person Re-identification

Awesome Person Re-Identification

Pytorch code for our CVPR'19 (oral) work: Unsupervised person re-identification by soft multilabel learning

Awesome Knowledge Distillation

DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing (ICCV 2019)

Code for Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data, ICCV 2019

Hyperbolic Graph Neural Networks

papers collection and understanding for video person re-identification

Datasets, Transforms and Models specific to Computer Vision

Deep learning person re-identification in PyTorch.

Person Re-ranking (CVPR 2017)

Awesome person re-identification

Supplementary code for the paper "Hyperbolic Image Embeddings".

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

A pytorch implementation of Maximum Mean Discrepancies(MMD) loss

Algorithm to extract the visual skeleton of the scanned objects. Mirror from the research group's private repo.

Partial implemention of KCNet

sota of reid model

Open MMLab Detection Toolbox

Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning

Code for reproducing the results of our "In Defense of the Triplet Loss for Person Re-Identification" paper.

Mask data and code for 'Mask-guided Contrastive Attention Model for Person Re-Identification' (CVPR-2018)

A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset

A simple GUI-based COCO-style JSON Polygon masks' annotation tool to facilitate quick and efficient crowd-sourced generation of annotation masks and bounding boxes. Optionally, one could choose to …