A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.

👁️ + 💬 + 🎧 = 🤖 Curated list of top foundation and multimodal models! [Paper + Code + Examples + Tutorials]

An open-source studio for prompt-driven video segmentation. Powered by SAM2 & Grounding DINO with a hybrid Cloud-Local architecture.

[TPAMI 2023] Generative Multi-Label Zero-Shot Learning

Multi-Model Real-Time Visual Recognition System - Supports YOLO, DETR, OWL-ViT, Grounding DINO, BLIP with REST API and WebSocket Streaming Inference | 多模型实时视觉识别系统 - 支持 YOLO、DETR、OWL-ViT、Grounding DINO、BLIP，提供 REST API 和 WebSocket 流式推理

Open-vocabulary part detection + LLM reasoning for context-aware AR assembly instructions — GroundingDINO + Llama 3.2 + Unity JSON output

YOLOv11 fine-tuning vs. zero-shot Grounding DINO for dental pathology detection in panoramic radiographs. Three-stage pipeline: detection, spontaneous recall, and LLM report generation. CBEB 2026.

Detection of similar (redundant) questions in a question bank

Semi-automated logo detection in multilingual videos using zero-shot detection (OWLv2), CLIP/SigLIP2 + FAISS retrieval, OCR, and audio transcription.

H.I.R.A. vision: open-vocabulary object detection on your webcam with YOLO-World (no dataset, no training). Part of the TYRIAN H.I.R.A. robot-arm project.

Zero-Shot Anime Character Detection and tracking system capable of Recognizing and Re-identifying characters without retraining for new classes

Type the name of any object. The system finds it, segments it, estimates its 3D pose, and outputs where a robot would grasp it. Zero training data required.

CLI wrapper for GroundingDINO, packaged for Leaxer

OWLv2 Zero-Shot Detector Test Code