Ultralytics YOLO 🚀

Ultralytics YOLO11 🚀

This demo is a simple software that I created using my studies and courses. It's designed for real-time object detection and tracking in video streams, using YOLOv8 for detection and ByteTrack for multi-object tracking. It is suitable for tracking objects in video footage, and can run on both GPU and CPU.

🤖 Explore curated resources for Human Activity Recognition (HAR), including datasets for action recognition, motion capture, and pose estimation.

🌐 Explore modular manifolds with clear code and techniques for advanced machine learning updates and training loops.

🚀 Build and deploy state-of-the-art computer vision models with Ultralytics YOLO, designed for speed and accuracy in real-time applications.

🖼️ Estimate 3D object poses from 2D images using advanced algorithms and Intel RealSense cameras; a robust toolkit for learning and research.

🧩 Calibrate your camera and estimate chessboard poses effortlessly with this modular OpenCV system for accurate visual processing.

🤖 Explore open-source robotics models and packages, including advanced vision-language-action systems for versatile applications and fine-tuning options.

🌟 Align diffusion processes with detailed human preferences to improve machine learning models for richer, more accurate outputs.

autoupdate paper list

ICCV 2023-2025 Papers: Discover cutting-edge research from ICCV 2023-25, the leading computer vision conference. Stay updated on the latest in computer vision and deep learning, with code included. ⭐ support visual intelligence development!

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

The collection of pre-trained, state-of-the-art AI models for ailia SDK

Markerless kinematics with any cameras — From 2D Pose estimation to 3D OpenSim motion

Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans

RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.

[NeurIPS 2025, Spotlight] Rectified Point Flow: Generic Point Cloud Pose Estimation

[ICCV 2025] ACE-G is an architecture and pre-training scheme to improve generalization for scene coordinate regression-based visual relocalization.

A Simple, Lightweight, and Extensible Serving Framework for X-AnyLabeling