Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Basic Infomation
About me
Page not in menu
This is a page not in th emain menu
Posts
Hyper Parameter Optimization
Published:
Neural network Hyper Parameter Optimization.
Handwritten ST-GCN
Published:
Handwritten the ST-GCN.
ST-GCN
Published:
ST-GCN structure.
Realize the Model Soup
Published:
Realize the Model Soup.
Simple summary about transformer in CV
Published:
Simple summary about transformer in CV.
ViT by pytorch code
Published:
ViT by pytorch code.
Image Generation note
Published:
Image Generation note.
HMR
Published:
Realize the HMR.
Human 3D reconstruction
Published:
Human 3D reconstruction by HMR.
yolov5 model.pt info
Published:
yolov5 model.pt information.
YOLOPose quick start
Published:
YOLO Pose quick start.
YOLOPose Loss
Published:
YOLO Pose Loss.
Deep Learning model quantization
Published:
Deep Learning model quantization.
YOLOpose code
Published:
YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss.
HRNet
Published:
About High resolution neural network.
SPP and SPPF(in YOLOv5)
Published:
SPP and SPPF（in YOLOv5）.
YOLOv5 structure
Published:
YOLOv5 structure.
Model soups
Published:
Model soups: averaging weights of multiple fine-tuned models.
Network Slimming
Published:
Learning Efficient Convolutional Networks through Network Slimming.
DINO
Published:
DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection.
Knowledge distillation
Published:
Knowledge distillation.
Backbone visualization
Published:
Backbone visualization.
(DeiT)Training data-efficient image transformers & distillation through attention
Published:
Training data-efficient image transformers & distillation through attention.
Unknown-Aware Object Detection
Published:
Solve out-of-distribution (OOD) problems.
DETR
Published:
End-to-End Object Detection with Transformers.
YOLOv1-YOLOv5
Published:
Handwritten the Resnet on torchvision.models.resnet.py.
Simple Multi-dataset Detection
Published:
Multi-dataset Detection.
Transformer on CV
Published:
About Transformer on Computer Vision.
Faster R-CNN (4. RoIHead)
Published:
Handwritten Faster RCNN RoI Head.
Faster R-CNN (3. RPN)
Published:
Handwritten Faster RCNN RPN.
Faster R-CNN (1. Summary)
Published:
Faster R-CNN Summary.
Faster RCNN (2. Transform and Backbone)
Published:
Handwritten the Faster RCNN Transform and Backbone.
Handwritten Resnet50+FPN
Published:
Handwritten the Resnet with FPN.
Handwritten Resnet
Published:
Handwritten the Resnet on torchvision.models.resnet.py.
patents
基于反向学习自适应花授粉的可见光定位方法及系统
Published:
This patent is about Visible Light Positioning System algorithm.
Download here
改进型RBF神经网络室内可见光定位方法及系统
Published:
This patent is about Visible Light Positioning System algorithm.
Download here
一种基于yolov5的目标检测模型、检测方法以及训练方法
Published:
Download here
一种体育运动评分模型数据增强方法、装置、设备和介质
Published:
This patent is about pose data augmentation.
Download here
一种基于Transformer的校园阳光跑人流量预测方法
Published:
Download here
一种预测光信道的方法以及灯源布局方法
Published:
Download here
一种无监督自主学习的全天候阳光跑人脸识别方法及系统
Published:
Download here
一种基于深度学习的太极拳动作评分方法及存储介质和电子设备
Published:
Download here
一种基于时空图卷积分割的跳绳识别网络模型的构建方法及其应用
Published:
Download here
一种轻量化体育运动自动识别和测试方法、装置及设备
Published:
Download here
portfolio
Visual Light Position System - 吉林省自然科学基金项目. (2020-2023)
Research for Visual Light Communication, Positoning System. 
Remote sensing segmentation. (2020)
Remote sensing segmentation 
Text classification. (2021)
News classification. 
Used car price data analysis. (2021)
Used car price data analysis 
Traffic Light Rec with Digital OCR. (2021)
Traffic Light Rec with Digital OCR. 
3D Skin structure. (2023)
3D Skin structure. 
Metro Intrusion Detection. (2023)
Metro Intrusion Detection. 
Taichi action evaluation. (2023)
Taichi action evaluation for rhythm and pose. 
Real time 3D Mesh on RTX 3080Ti. (2024)
Face style transpose. 
Anime Face. (2024)
Face style transpose. 
Monocular depth estimation. (2024)
Deploy for monocular depth estimation. 
3D Reconstraction from Multi-view. (2024)
3D Reconstraction from Multi-view 
Fake Face. (2024)
Fake Face. 
Knowledge Graph. (2024)
Knowledge Graph. 
2024昇腾AI创新大赛(企业赛道). (2024)
福建赛区 - 智能阳光跑. 
LLM x RAG. (2024)
RAG. 
Sport Analysis by Large Model. (2024)
Sport analysis. 
Extra High precision 3D Pull-Up. (2024)
Pull up scoring DEMO. 
Auto perspective for scale line. (2024)
Auto perspective for scale line. 
南拳, 长拳, 技巧组合动作评分, 北京市体育中考(Beijing PEE). (2025)
Action scoring DEMO. 
DeepSeek. (2025)
Research, Deploy and Apply for DeepSeek. 
乒乓球轨迹跟踪和得分计算, 北京市体育中考(Beijing PEE). (2025)
Pingpong scoring DEMO. 
publications
基于KPCA-K-means++和GA-LMS模型的改进RBF神经网络室内可见光定位
Published in Acta Optica Sinica, 2021
This paper is about Visible Light Positioning System algorithm.
Download here
稀疏训练指纹库融合MMPSO-ELM室内可见光定位
Published in Laser Techno, 2021
This paper is about Visible Light Positioning System algorithm.
Download here
基于并行全连接卷积神经网络模型的室内可见光信道的最优灯源布局
Published in Acta Optica Sinica, 2022
This paper is about Visible Light Communication channel and Light algorithm.
Download here
基于GAN指纹库的卷积神经网络室内可见光信道模型
Published in Journal of Optoelectronics.Laser (2023), 2023
This paper is about Visible Light Communication channel and Light algorithm.
Download here
S $ ^3 $ GCN: Sport Scoring Siamese Graph Convolution Network
Published in 2024 IEEE International Conference on Image Processing (ICIP), 2024
This paper is about action scoring.
Download here
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.