Name: Dingkang Liang
Type: User
Company: Huazhong University of Science & Technology
Bio: A PHD student at VLR Group, HUST.
Research Intern at Baidu.
Location: Luoyu Road 1037, Wuhan, China
Blog: https://dk-liang.github.io/
Dingkang Liang's Projects
[IJCV] An implementation of AutoScale localization-based method
An implementation of AutoScale regression-based method
A curated list of awesome computer vision resources
Awesome Crowd Counting
Awesome GPT-4 with Applications. This is a collection of resources related to GPT-4, including news, official documents, demo and applications.
A list of awesome Robotics resources
Collect some resource about Segment Anything (SAM), including the latest papers and demo
Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)
2018-bibtechnology
Implementation for CenterFormer: Center-based Transformer for 3D Object Detection (ECCV 2022)
[ECCV 2022] An End-to-End Transformer Model for Crowd Localization
[CVPR 2023] CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
[CVPR 2024] Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
[ECCV 2022] DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection.
[IEEE TMM] Focal Inverse Distance Transform Maps for Crowd Localization
PyTorch implementations of the paper: "Learning Independent Instance Maps for Crowd Localization"
OpenMMLab's next-generation platform for general 3D object detection.
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
PointMamba: A Simple State Space Model for Point Cloud Analysis
A toolbox for skeleton-based action recognition.
A demo for using C++ to inference the pytorch model
SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model
[SCIS] TransCrowd: Weakly-Supervised Crowd Counting with Transformers