weijiawu

Awesome-RL-for-Multimodal-Foundation-Models. 📖 This is a repository for organizing papers, codes and other resources related to Visual Reinforcement Learning.

DiffuMask. [ICCV2023] DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models

TransDETR. [IJCV 2024] TransDETR: End-to-end Video Text Spotting with Transformer

ParaDiffusion. [IJCV 2025] Paragraph-to-Image Generation with Information-Enriched Diffusion Model

TransVTSpotter. A new video text spotting framework with Transformer

BOVText-Benchmark. [NeurIPS2021] BOVText: A Large-Scale, Multidimensional Multilingual Dataset for Video Text Spotting

Awesome-Synthetic-Data-for-Perception-Task.

SyntoReal_STD. HHH

Polygon-free-Unconstrained-Scene-Text-Detection-with-Box-Annotations. Unconstrained Text Detection with Box Supervisionand Dynamic Self-Training

information-extraction-of-express. 基于OpenCV、目标检测对快递单进行识别并提取有用的信息进行处理

CisDQ. Python

Classification_with_Cleanlab. Classification_with_Cleanlab is an open source image classification toolbox using Cleanlab based on PyTorch. The toolbox efficiently utilize Cleanlan to learn with noisy labels and finding label errors in datasets.

CoText. Python

Yibao-cup_competition. oo

DiffusionMask. HTML

Domain-Adaptive-Collection.

TextVR. TextVR:A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension. and StarVR: secne text aware video retrieval

Scene-Text-Detection-and-Recognition-benchmark. C++

Blemish_Detection_of_aluminium. Jupyter Notebook

My_Note.

Pytorch_Classification. weijiawu/Pytorch_Classification

Scene_Text_Paper_Newest. It is a personal summary concerning newest scene text paper in 2019

awesome-domain-adaptation. A collection of AWESOME things about domian adaptation

TextAsLine. A weakly-supervised text detector named 'Texts As Lines' and a set of training methods, which greatly simplify the annotation process and improve the speed without losing accuracy.

ParaDiffusionPage. HTML

Tensorflow_DL. Jupyter Notebook

draganything_page. JavaScript

kaggle_driver_state_detection. Jupyter Notebook

DatasetDM_page. Official code for 'DatasetDM:Synthesizing Data with Perception Annotations Using Diffusion Models'

rrcevaluation. JavaScript

Segment-Anything-for-Stable-Diffusion-WebUI. Python

weijiawu.github.io. HTML

MovieAgent. JavaScript

weijiawu.

MovieBench. JavaScript