Now showing items 1-4 of 108

• Exploiting multimodality and structure in world representations ﻿

An essential aim of artificial intelligence research is to design agents that will eventually cooperate with humans within the real world. To this end, embodied learning is emerging as one of the most important efforts ...
• Neural approaches to discourse coherence: modeling, evaluation and application ﻿

Discourse coherence is an important aspect of text quality that refers to the way different textual units relate to each other. In this thesis, I investigate neural approaches to modeling discourse coherence. I present a ...
• Compressive sensing of images and video: towards low-complexity, real-time operation ﻿

Compressive Sensing (CS) acquires sparse signals with far fewer measurements than samples required by the classical Nyquist sampling theorem, at the cost of more computationally intensive reconstruction. Video Block ...
• Availability, Integrity, and Confidentiality for Content Centric Network internet architectures ﻿

The Internet as we know it today, despite being the result of a series of accidents of choices'' in Prof. Jon Crowcroft's words, has undoubtedly been an amazing success story. However, it has been constantly challenged ...