A community-driven replacement for JSQMessagesViewController

A SwiftUI Chat UI framework with fully customizable message cells and a built-in media picker

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Run Segment Anything Model 2 on a live video stream

Testcontainers is a Python library that providing a friendly API to run Docker container. It is designed to create runtime environment to use during your automatic tests.

A software project to provide the target tracking community with a framework for the development and testing of tracking algorithms.

A collection of postmortems. Sorry for the delay in merging PRs!

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

BodyPix model demo application for Google Coral

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) fo…

This repository contains code for object detection and tracking in videos using the YOLOv10 object detection model and the DeepSORT algorithm.

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

Ultimate camera streaming application with support RTSP, RTMP, HTTP-FLV, WebRTC, MSE, HLS, MP4, MJPEG, HomeKit, FFmpeg, etc.

DeepFashion2 Dataset https://arxiv.org/pdf/1901.07973.pdf

SOTA Re-identification Methods and Toolbox

Tracking-by-detection framework supporting various algorithms.

Official PyTorch implementation of SparseTrack (the new version of code will come soon)

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

https://arxiv.org/abs/2302.11813

Multiple Object Tracking as ID Prediction

[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

Person Re-Identification (ReID) using lightweight Deep Learning model.

Torchreid: Deep learning person re-identification in PyTorch.

A General-purpose Person Re-identification Task with Instructions

[ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity

[ICCV-2021] TransReID: Transformer-based Object Re-Identification