Efficient Track Anything

Pytorch Implementation of "SMITE: Segment Me In TimE"

A generative world for general-purpose robotics & embodied AI learning.

[NeurIPS2024] Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model

ZIM: Zero-Shot Image Matting for Anything

Effortless data labeling with AI support from Segment Anything and other awesome models.

Tracking Any Point (TAP)

CoTracker is a model for tracking any point (pixel) on a video.

✨✨Latest Advances on Multimodal Large Language Models

Official repo for CVPR2024 paper "Single Domain Generalization for Crowd Counting"

Next-Token Prediction is All You Need

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

High-resolution models for human tasks.

SymPy with PythonCall backend (not PyCall)

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation

Muggled SAM: Segmentation without the magic

Minimal solvers for calibrated camera pose estimation

face-cluster-by-infomap 一种无监督人脸聚类方法，在开源数据集上取得SOTA效果

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

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 th…

Gaussian Splatting in pure Julia

[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…

Resources for Multiple Object Tracking (MOT)

Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

A State-Space Model with Rational Transfer Function Representation.

This project is a scalable unified framework for deep graph clustering.

A Julia-based job scheduler and workload manager inspired by Slurm, PBS and Crontab.

Universal Scene Description