杜子文

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

collecting books, papers and docs.

2025年全网最全即插即用模块，免费分享！CVPR2025，AAAI2025，ICLR2025，TNNLS2025，arXiv2025......包含人工智能全领域（机器学习、深度学习等），适用于图像分类、目标检测、实例分割、语义分割、全景分割、姿态识别、医学图像分割、视频目标分割、图像抠图、图像编辑、单目标跟踪、多目标跟踪、行人重识别、RGBT、图像去噪、去雨、去雾、去阴影、去模糊、超分辨率、去反光、去摩尔纹、图像恢复、图像修复、高光谱图像恢复、图像融合、图像上色、高动态范围成像、视频与图像压缩、3D点云、3D目标检测、3D语义分割、3D姿态识别等各类计算机视觉和图像处理任务，以及自然语言处理、大语言模型、多模态等其他各类人工智能相关任务。持续更新中......

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Visualize how medical segmentation models learn across epochs: masks, errors, features, boundaries, and uncertainty.

将做科研时的工程化agent经验/限制/harness，存放在这里，以方便直接使用于项目中

CMR实践

onelittle、twolittle、baby ducks

CLI4ITK-SNAP: An agent-friendly command-line harness for ITK-SNAP workflows.

河南中医药紫癜性肾炎项目

心肌炎电镜项目

MedSAM3复现

sam3formed

我的orbit拆分仓库

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

The code of " Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network"

[CVPR2025] Number it: Temporal Grounding Videos like Flipping Manga

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding

Custom ava dataset, Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions

MOT using deepsort and yolov3 with pytorch

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

Reference PyTorch implementation and models for DINOv3，一个强大的视觉模型家族，在多种计算机视觉任务上取得优异成绩。

Ultralytics YOLO 🚀

🎬 卡卡字幕助手 | VideoCaptioner - 基于 LLM 的智能字幕助手 - 视频字幕生成、断句、校正、字幕翻译全流程处理！- A powered tool for easy and efficient video subtitling.

The Hugging Face course on Transformers with CN

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

NLP数据集

A treasure chest for visual classification and recognition powered by PaddlePaddle

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.

图像识别数据集，有很多的图片，和图片对应的标签

CVPR 2025 论文和开源项目合集

A Collection of application ideas which can be used to improve your coding skills.