This paper presents three methods that can be used to recognize paraphrases. They all employ string similarity measures apshallow abstractions of the input sentences, and a Maximu...
In this research we aim to detect subjective sentences in multimodal conversations. We introduce a novel technique wherein subjective patterns are learned from both labeled and un...
In this paper, a new class of audio representations is introduced, together with a corresponding fast decomposition algorithm. The main feature of these representations is that th...
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...
We develop an algorithm for finding and kinematically tracking multiple people in long sequences. Our basic assumption is that people tend to take on certain canonical poses, even...