Výsledky vyhledávání

Report

Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning

Autor: Perez, Fabian, Lopez, Jhon, Arguello, Henry

In the era of cloud computing and data-driven applications, it is crucial to protect sensitive information to maintain data privacy, ensuring truly reliable systems. As a result, preserving privacy in deep learning systems has become a critical conce

Externí odkaz: http://arxiv.org/abs/2404.05828

Zobrazit plný text záznamu

Report

Privacy-preserving Optics for Enhancing Protection in Face De-identification

Autor: Lopez, Jhon, Hinojosa, Carlos, Arguello, Henry, Ghanem, Bernard

The modern surge in camera usage alongside widespread computer vision technology applications poses significant privacy and security concerns. Current artificial intelligence (AI) technologies aid in recognizing relevant events and assisting in daily

Externí odkaz: http://arxiv.org/abs/2404.00777

Zobrazit plný text záznamu

Report

Depth Estimation from a Single Optical Encoded Image using a Learned Colored-Coded Aperture

Autor: Lopez, Jhon, Vargas, Edwin, Arguello, Henry

Depth estimation from a single image of a conventional camera is a challenging task since depth cues are lost during the acquisition process. State-of-the-art approaches improve the discrimination between different depths by introducing a binary-code

Externí odkaz: http://arxiv.org/abs/2309.08033

Zobrazit plný text záznamu