Voluminous medical images are generated daily. They are critical assets for medical diagnosis, research, and teaching. To facilitate automatic indexing and retrieval of large medic...
The authors present TWIG, a visually grounded wordlearning system that uses its existing knowledge of vocabulary, grammar, and action schemas to help it learn the meanings of new ...
Orthogonal information present in the video signal associated with the audio helps in improving the accuracy of a speech recognition system. Audio-visual speech recognition involv...
Tanveer A. Faruquie, Abhik Majumdar, Nitendra Rajp...
This paper presents a method for visual object categorization based on encoding the joint textural information in objects and the surrounding background, and requiring no segmenta...
Alireza Tavakoli Targhi, Andrzej Pronobis, Heydar ...
In this paper, we present a method that allows us to recover the trajectory of a vehicle purely from monocular omnidirectional images very accurately. The method uses a combination...
Davide Scaramuzza, Friedrich Fraundorfer, Marc Pol...