keyhsw's Stars
dangweili/RAP
A Richly Annotated Pedestrian Dataset for Person Retrieval in Real Surveillance Scenarios
gjy3035/Awesome-Crowd-Counting
Awesome Crowd Counting
zhongyingji/APNet
Robust Partial Matching for Person Search in the Wild
KaiyangZhou/pytorch-center-loss
Pytorch implementation of Center Loss
yuanli2333/Teacher-free-Knowledge-Distillation
Knowledge Distillation: CVPR2020 Oral, Revisiting Knowledge Distillation via Label Smoothing Regularization
houqb/SPNet
Code for our CVPR2020 paper "Strip Pooling: Rethinking Spatial Pooling for Scene Parsing"
microsoft/hnms
Hashing-based Non-Maximum Suppression
facebookresearch/detr
End-to-End Object Detection with Transformers
lengyanyu258/xiangqiboardjs
JavaScript Chinese chess/cchess/Xiangqi board
Leotju/MGAN
Mask-Guided Attention Network for Occluded Pedestrian Detection. (ICCV'19)
xingkongliang/Pedestrian-Detection
Pedestrian Detection Papers
zhangliliang/RPN_BF
RPN+BF
rainofmine/Repulsion_Loss
Pytorch implementation of Repulsion Loss on RetinaNet
Shualite/Yet-Another-EfficientDet-Pytorch
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.
Shualite/deocclusion
Code for our CVPR 2020 work.
generalized-iou/Detectron.pytorch
Zzh-tju/DIoU-pytorch-detectron
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression (AAAI 2020)
generalized-iou/g-darknet
darknet with GIoU
diggerdu/Generalized-Intersection-over-Union
Unofficial Pytorch Implementation of GIoU:[CVPR2019]Generalized Intersection over Union
WarBean/tps_stn_pytorch
PyTorch implementation of Spatial Transformer Network (STN) with Thin Plate Spline (TPS)
dvlab-research/GridMask
Dingyuan-Zheng/maskPS
Segmentation Mask Guided End-to-End Pereson Search
CyC2018/CS-Notes
:books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计
mbbremner/PersonSearchCLSA
This is a reconstruction from scratch of a deep network, based on a technique outlined in the compouter vision paper "Person Search by Multi-Scale Matching". The model is built upon a modified ResNet-50 backbone. The purpose of the technique is to boost the performance of person search by reinforcing semantic alignment across layers.
serend1p1ty/person_search
PyTorch implementation of CVPR 2017 "Joint Detection and Identification Feature Learning for Person Search"
Sense-X/TSD
1st place models in Google OpenImage Detection Challenge 2019
Sophia-11/AI-Conference
The most complete list of AI top meetings
SHI-Labs/Decoupled-Classification-Refinement
Revisiting RCNN: On Awakening the Classification Power of Faster RCNN (ECCV 2018)
miraclewkf/ResNeXt-PyTorch
hangg7/deformable-kernels
Deforming kernels to adapt towards object deformation. In ICLR 2020.