Highlights
- Pro
Lists (27)
Sort Name ascending (A-Z)
3d
annotation
benchmark
chatgpt
coding
detection
edge
face
forecast
gps
image-matching
kaggle
mahjong
medical
metric learning
model compression
nlp
ocr
pose
remote sensing
rl
segmentation
sequence
time-series
tool
tracking
video
Stars
The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
Solution for the CMI - Detect Behavior with Sensor Data Kaggle Competition
Next-generation Albumentations: dual-licensed for open-source and commercial use
RadImageNet, a pre-trained convolutional neural networks trained solely from medical imaging to be used as the basis of transfer learning for medical imaging applications.
"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)
https://www.kaggle.com/competitions/czii-cryo-et-object-identification/discussion/561401
Connected components on discrete and continuous multilabel 3D & 2D images. Handles 26, 18, and 6 connected variants; periodic boundaries (4, 8, & 6)
collection of articles about PhD life written in 🇯🇵
A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model
[ICLR 2024 Oral] Supervised Pre-Trained 3D Models for Medical Image Analysis (9,262 CT volumes + 25 annotated classes)
A synthetic data generator for text recognition
YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
This is the implementation of the 4th place solution (yu4u's part) for RSNA 2024 Lumbar Spine Degenerative Classification at Kaggle.
AI Edge Quantizer: flexible post training quantization for LiteRT models.
Official repo for VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset..
GNSS satellite visibility simulation from Google Earth
Supporting PyTorch models with the Google AI Edge TFLite runtime.
Lightning ⚡️ fast forecasting with statistical and econometric models.
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Lightweight Python library for adding real-time multi-object tracking to any detector.
YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]
[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥