RF-DETR is a real-time transformer architecture for object detection, instance segmentation, and keypoint detection (preview) developed by Roboflow. Built on a DINOv2 vision transformer backbone, ...
Abstract: Utilizing multiview infrared images to collaboratively identify the types of surface ship targets is a feasible approach in practice. This article proposes a fine-grained object recognition ...
Abstract: Identifying novel human-object interaction (HOI) classes with scarce data is a challenging and crucial task in computer vision. Existing methods mainly use coarse global visual information ...
This is a fairly simple image classification Python script that I wrote as a project deliverable for my 2014 Machine Learning class at the Polytechnic University of Catalonia (UPC), back when I was ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results