PeizeSun
PhD student, The University of Hong Kong, Computer Vision
The University of Hong KongHong Kong
Pinned Repositories
DanceTrack
[CVPR2022] DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion
VLPart
[ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation
LlamaGen
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
3dv_tutorial
An Invitation to 3D Vision: A Tutorial for Everyone
llamagen
[Project Page] Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
MedicalDigitalHuman
MedicalDigitalHuman: Skin, Skeleton and Organ
OneNet
[ICML2021] What Makes for End-to-End Object Detection
PolarMask
Code for 'PolarMask: Single Shot Instance Segmentation with Polar Representation'
SparseR-CNN
[CVPR2021, PAMI2023] End-to-End Object Detection with Learnable Proposal
TransTrack
Multiple Object Tracking with Transformer
PeizeSun's Repositories
PeizeSun/SparseR-CNN
[CVPR2021, PAMI2023] End-to-End Object Detection with Learnable Proposal
PeizeSun/OneNet
[ICML2021] What Makes for End-to-End Object Detection
PeizeSun/TransTrack
Multiple Object Tracking with Transformer
PeizeSun/llamagen
[Project Page] Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
PeizeSun/MedicalDigitalHuman
MedicalDigitalHuman: Skin, Skeleton and Organ
PeizeSun/ControlNet
Let us control diffusion models!
PeizeSun/detectron2
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
PeizeSun/VLPart
PeizeSun/AdelaiDet
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
PeizeSun/CenterNet
Object detection, 3D detection, and pose estimation using center point detection:
PeizeSun/CenterNet-better
An easy to understand and better performance version of CenterNet
PeizeSun/CenterNet-CondInst
Instance Segmentation based on CenterNet and CondInst
PeizeSun/CenterTrack
Simultaneous object detection and tracking using center points.
PeizeSun/Deformable-DETR
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
PeizeSun/Detic
Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".
PeizeSun/detr
End-to-End Object Detection with Transformers
PeizeSun/FairMOT
[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking
PeizeSun/ifzhang
PeizeSun/Mask2Former
Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
PeizeSun/object_localization_network
Learning Open-World Object Proposals without Learning to Classify
PeizeSun/PeizeSun
PeizeSun/peizesun.github.io
personal website
PeizeSun/Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
PeizeSun/Towards-Realtime-MOT
Joint Detection and Embedding for fast multi-object tracking
PeizeSun/ToyFace
Toy examples of face recognition loss
PeizeSun/ViT-pytorch
Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
PeizeSun/VLDet
[ICLR 2023] PyTorch implementation of VLDet (https://arxiv.org/abs/2211.14843)
PeizeSun/whai362
PeizeSun/yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
PeizeSun/YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/