Stars
Learning Chinese Character style with conditional GAN
🎮 An open-source game speed modifier.[一款开源的游戏变速器]
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
[ICLR 2025] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)
PyTorch code and models for the DINOv2 self-supervised learning method.
VideoX: a collection of video cross-modal models
(CVPR2023/TPAMI2024) Integrally Pre-Trained Transformer Pyramid Networks -- A Hierarchical Vision Transformer for Masked Image Modeling
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
[Accepted by ICCV2025] Official code of the paper "From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision"
CVPR 2025: Frequency Dynamic Convolution for Dense Image Prediction
Large World Model -- Modeling Text and Video with Millions Context
Writing AI Conference Papers: A Handbook for Beginners
EVA Series: Visual Representation Fantasies from BAAI
This repository is a paper digest of Transformer-related approaches in visual tracking tasks.
[CVPR 2025] Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"
Official Code for "MITracker: Multi-View Integration for Visual Object Tracking"
[ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking