GitHub

OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision

OV-DQUO is an open-vocabulary detection framework that learns from open-world unknown objects through wildcard matching and contrastive denoising training methods, mitigating performance degradation ...
IEEE

MMI-Det: Exploring Multi-Modal Integration for Visible and Infrared Object Detection

Abstract: The Visible-Infrared (VIS-IR) object detection is a challenging detection task, which combines visible and infrared data to give information on the category and location of objects in the ...

Microsoft unveils new AI models to lessen reliance on OpenAI and lower costs for developers

At its Build developer conference, Microsoft announced a series of generative AI models to try and crack a market controlled ...
IEEE

PtbNet: Based on Local Few-Shot Classes and Small Objects to Accurately Detect PTB

Abstract: Pulmonary Tuberculosis (PTB) is one of the world’s most infectious illnesses, and its early detection is critical for preventing PTB. Digital Radiography (DR) has been the most common and ...

I Gave My OpenClaw Agent a Physical Body

I recently gave my OpenClaw a real robot arm to play with. The results just about blew my own neural network. The AI agent was able to configure the arm, use it to see and slowly grab things, and even ...
GitHub

Open World Object Detection in the Era of Foundation Models

[2024.1.5] Initial release of the RWD dataset. I will be updating the arXiv after a bug was found, causing some variations to the original numbers. The proposed Real-World Object Detection (RWD) ...