We present a holistic data-driven approach to image description generation, exploiting the vast amount of (noisy) parallel image data and associated natural language descriptions ...
Polina Kuznetsova, Vicente Ordonez, Alexander C. B...
This paper studies the influence of n-gram language models in the recognition of sung phonemes and words. We train uni-, bi-, and trigram language models for phonemes and bi- and...
Abstract—We consider adapting the transmission rate to maximize the goodput, i.e., the amount of data transmitted without error, over a continuous Markov flat-fading wireless ch...
We propose a type and effect system for authentication protocols built upon a tagging scheme that formalizes the intended semantics of ciphertexts. The main result is that the val...
Berners-Lee’s compelling vision of a Semantic Web is hindered by a chicken-and-egg problem, which can be best solved by a bootstrapping method — creating enough structured dat...