Wuhan

Ziwen Chen

Advanced
@chenziwenhaoshuai

BioPage：chenziwenhaoshuai.github.io PhD in HUST, Time series, Computer vision, Multi-task learning, LLM

Vision-KAN. KAN for Vision Transformer

256

Vision-Mamba2. Vision Mamba 2: More Efficient Visual Representation Learning with State Space Duality

27

CliffordNet-pytorch. Unofficial CAN

21

Word2Latex-Agent. LLM agent-driven conversion of Word documents to any LaTeX template

10

TS-CLIP. [EMNLP-2025 main] TS-CLIP: Time Series Understanding by CLIP

10

FuseAnyFocus. Fuse Any Focus: Multi-focus Image Fusion via Focal Plane Segmentation

9

WaterRemind. 一款用来提醒喝水的小杯垫

5

POLO. 【CVPR 2025 workshop】POLO: Pose Estimation with One-stage Location-sensitive Coding

5

ZoomViT. 【ICLR-2026】Vision Transformers Need Zoomer: Efficient Vision Transformers with Local Zooming

4

Auto_Christmas. This program can detect your face and add an Christams hat on the top of your head.

4

FishNet. FishNet: One Stage to Detect, Segmentation and Pose Estimation

4

Adaptive_clipping. This project provides an adaptive clipping algorithm suitable for the target detection process

4

fastbackup. 代码本地自动备份只需一行导入

3

TimeVQGAN. TimeVQGAN: Learning Universal Discrete Representations for General Time-series Analysis

3

SenseAir_OLED. use senseair s8 to test co2 ppm

2

Huggingface_Tools. 更适合中国宝宝的Huggingface大数据集下载器

2

YOLOv5_Depth. YOLOv5_Depth: use YOLOv5 to detect depth image

2

Markdown2PDF. arkdown to PDF Converter

2

Open-DeepL. open deepl translater

2

YOLOCar. Use YOLOv5 to detect traffic flow and speed

1

chenziwenhaoshuai.github.io. HTML

1

Ichat. 一个利用微软小冰来替你回复（敷衍）微信消息的脚本

1

ExamForXingrui. HTML

1

AlexNet. Alex

1

crack-iyf. JavaScript

1
25
Apply