A scalable, distributed, collaborative, document-graph database, for the realtime web

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how t…

FoundationDB - the open source, distributed, transactional key-value store

Sharp Monocular View Synthesis in Less Than a Second

Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

A curated list of awesome System Design (A.K.A. Distributed Systems) resources.

Research code for CVPR 2021 paper "End-to-End Human Pose and Mesh Reconstruction with Transformers"

Run Segment Anything Model 2 on a live video stream

V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties

Reproduce AlignedReID: Surpassing Human-Level Performance in Person Re-Identification, using Pytorch.

[CVPR2022] DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion

Multiple Object Tracking with Transformer

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

Open-source platform to build and deploy AI agent workflows.

A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models such as YOLO, FastVLM, and more.

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

Official implementation of "A Simple Visual-Textual Baseline for Pedestrian Attribute Recognition" [TCSVT 2022]

Pytorch Pedestrian Attribute Recognition: A strong PyTorch baseline for pedestrian attribute recognition and multi-label classification.

[NeurIPS2024] PLIP: Language-Image Pre-training for Person Representation Learning

Official implementation for "CLIP-ReID: Exploiting Vision-Language Model for Image Re-identification without Concrete Text Labels" (AAAI 2023)

Text-Enhanced Zero-Shot Action Recognition

Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

creating Anime Avataar from a facial image

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone