yangkang's repositories
YOLO-POSE-Bytetrack-STGCN
YOLO-POSE was used for key point detection, Bytetrack for tracking, and STGCN for fall and other behavior recognition
3DMPPE_POSENET_RELEASE
Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
albumentations
Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
ByteTrack_ReID
ByteTrack with ReID module following the paradigm of FairMOT, tracking strategy is borrowed from FairMOT/JDE.
CenterNet-better
An easy to understand and better performance version of CenterNet
centerX
This repo is implemented based on detectron2 and centernet
Deep-Learning-for-Tracking-and-Detection
Collection of papers, datasets, code and other resources for object tracking and detection using deep learning
EagerMOT
Official code for "EagerMOT: 3D Multi-Object Tracking via Sensor Fusion" [ICRA 2021]
eagermot_ms
MindSpore verion of EagerMOT
EasyCV
An all-in-one toolkit for computer vision
GANet
A Keypoint-based Global Association Network for Lane Detection. Accepted by CVPR 2022
HAKE-Action-Torch
HAKE-Action in PyTorch
IoU-Uniform-R-CNN
Codes for paper: "IoU-Uniform R-CNN: Breaking Through the Limitations of RPN"
JRMOT_ROS
Source code for JRMOT: A Real-Time 3D Multi-Object Tracker and a New Large-Scale Dataset
mmaction
An open-source toolbox for action understanding based on PyTorch
MPF_GRR_SLT
A width-based Monocular Person Following system with Global descriptor, Ridge Regression online target classifier and Short-Long-Term sampling strategy (MPF_GRR_SLT)
open_clip
An open source implementation of CLIP.
Pedestron
[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021
person_following_bot
This is a deep learning based robot which follows a person in dynamic environment.
ResNeSt
ResNeSt: Split-Attention Network
StreamYOLO
Real-time Object Detection for Streaming Perception, CVPR 2022
TracKit
[ECCV'20] Ocean: Object-aware Anchor-Free Tracking
TraDeS
Track to Detect and Segment: An Online Multi-Object Tracker (CVPR 2021)
UniDetector
Code release for our CVPR 2023 paper "Detecting Everything in the Open World: Towards Universal Object Detection".
video_analyst
A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.
Yet-Another-EfficientDet-Pytorch
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.