XJhaoren

3D-R2N2-PyTorch

PyTorch version of 3D-R2N2

3D-ResNets-PyTorch

3D ResNets for Action Recognition (CVPR 2018)

Academic-Group

AdaBound

An optimizer that trains as fast as Adam and as good as SGD.

AI-Toolbox

Algorithm Engineer Toolbox, for the purpose of quickly iterating new ideas

ann-benchmarks

Benchmarking approximate nearest neighbors. Note: This is an archived version from our SISAP 2017 paper, see below.

awesome-cbir-papers

📝Awesome and classical image retrieval papers

cnnimageretrieval-pytorch

CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

IME_layer

Code for Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-scale Image Retrieval

PWA

Code for Unsupervised Part-based Weighting Aggregation of Deep Convolutional Features for Image Retrieval

XJhaoren/AI-Toolbox

Algorithm Engineer Toolbox, for the purpose of quickly iterating new ideas

XJhaoren/ann-benchmarks-1

Benchmarks of approximate nearest neighbor libraries in Python

XJhaoren/awesome-Gesture-Recognition

resources about Gesture Recognition

XJhaoren/awesomeCV

记录state-of-art计算机视觉相关论文。

XJhaoren/Class-balanced-loss-pytorch

Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"

XJhaoren/coco-annotator

:pencil2: Web-based image segmentation tool for object detection, localization, and keypoints

XJhaoren/cvpr2020

cvpr2020/cvpr2019／cvpr2018/cvpr2017 papers，极市团队整理

XJhaoren/CVPR21Chal-SLR

This repo contains the official code of our work SAM-SLR which won the CVPR 2021 Challenge on Large Scale Signer Independent Isolated Sign Language Recognition.

XJhaoren/deep-person-reid

Deep learning person re-identification in PyTorch.

XJhaoren/DEKR

This is an official implementation of our CVPR 2021 paper "Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression" (https://arxiv.org/abs/2104.02300)

XJhaoren/EfficientNet-PyTorch

A PyTorch implementation of EfficientNet

XJhaoren/FairMOT

A simple baseline for one-shot multi-object tracking

XJhaoren/faiss

A library for efficient similarity search and clustering of dense vectors.

XJhaoren/finegan

FineGAN: Unsupervised Hierarchical Disentanglement for Fine-grained Object Generation and Discovery

XJhaoren/HigherHRNet-Human-Pose-Estimation

This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)

XJhaoren/Hybrid-Attention-based-Decoupled-Metric-Learning

Caffe implementation of "Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval"

XJhaoren/image-matching-benchmark

Public release of the Image Matching Benchmark: https://vision.uvic.ca/image-matching-challenge

XJhaoren/insightface

Face Analysis Project on MXNet

XJhaoren/InterHand2.6M

Official PyTorch implementation of "InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image", ECCV 2020

XJhaoren/MedicalNet

Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.

XJhaoren/Mimic3DWeb

XJhaoren/nanodet

⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

XJhaoren/Person_reID_baseline_pytorch

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

XJhaoren/PyRetri

Open source deep learning based unsupervised image retrieval toolbox based on PyTorch🔥

XJhaoren/SOSNet

Pretrained pytorch model for the SOSNet descriptor [CVPR 2019]

XJhaoren/tpu

Reference models and tools for Cloud TPUs.

XJhaoren/TransT

Transformer Tracking (CVPR2021)

XJhaoren/vcpkg

C++ Library Manager for Windows, Linux, and MacOS

XJhaoren/XJhaoren.github.io

XJhaoren/Yet-Another-EfficientDet-Pytorch

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.