Can I read Page 1 on EtoBox?

Page 1 by nisha001phd23 is a document available to read on EtoBox.

What is Page 1 about?

This paper introduces a Disentangled Object-Attribute Detection Framework that combines YOLOv8 and DINOv2 to improve object detection by capturing fine-grained semantic attributes. The model, tested on the Visual Genome dataset, achieved an average confidence of 91.5% and a precision of 56%, demonstrating its effectiveness in recognizing complex object-attribute pairs. This framework offers a computationally efficient solution for applications such as image captioning.

Author

nisha001phd23

Language

EN