zimenglan-sysu-512

Focal-Loss

loss layer of implementation

paper-note

fddb-eval-code

a code for eval the mAP curves of the public face dataset FDDB

pose_action_caffe

HanLP

汉语言处理包 中文分词 词性标注 命名实体识别 依存句法分析 关键词提取 自动摘要 短语提取 拼音 简繁转换

maskrcnn-benchmark

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

bier

Cleaned up reference implementation of BIER: Boosting Independent Embeddings Robustly.

cascade-rcnn

Caffe implementation of multiple popular object detection frameworks

ccnn

Counting CNN and Hydra CNN

convolutional-pose-machines-release

Code repository for Convolutional Pose Machines

CT-Net

[ICLR2021] CT-Net: Channel Tensorization Network for Video Classification

DANet

Dual Attention Network for Scene Segmentation (CVPR2019)

Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Detectron-Cascade-RCNN

Cascade R-CNN in Detectron

detectron2

Detectron2 is FAIR's next-generation research platform for object detection and segmentation.

EfficientNet-PyTorch

A PyTorch implementation of EfficientNet

GCA-Matting

Natural Image Matting via Guided Contextual Attention

Heated_Up_Softmax_Embedding

Project page for Heated-up Softmax Embedding

KCFcpp

C++ Implementation of KCF Tracker

mmdetection

Open MMLab Detection Toolbox

mscnn

NormSoftmax

A PyTorch implementation of NormSoftmax based on BMVC 2019 paper "Classification is a Strong Baseline for Deep Metric Learning"

NTS-Net

This is a PyTorch implementation of the ECCV2018 paper "Learning to Navigate for Fine-grained Classification" (Ze Yang, Tiange Luo, Dong Wang, Zhiqiang Hu, Jun Gao, Liwei Wang).

ObjectDetection-OneStageDet

pose-hg-train

Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"

reid-strong-baseline

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

retrieval-2016-deepvision

Faster R-CNN features for Instance Search

RRPN

Source code of RRPN ---- Arbitrary-Oriented Scene Text Detection via Rotation Proposals

SoftTeacher

Semi-Supervised Learning, Object Detection, ICCV2021

STAM

Official implementation of "An Image is Worth 16x16 Words, What is a Video Worth?" (2021 paper)