Symbol spotting problem requires feature extraction strategies able to generalize from training samples and to localize the target object while discarding most part of the image. ...
To bridge the semantic gap in content-based image retrieval, detecting meaningful visual entities (e.g. faces, sky, foliage, buildings etc) in image content and classifying images...
The interest in registering a set of images has quickly risen in the field of medical image analysis. Mutual information (MI) based methods are well-established for pairwise regist...
Bing Ma, Ramkrishnan Narayanan, Hyunjin Park, Alfr...
Lip reading provides useful information in speech perception and language understanding, especially when the auditory speech is degraded. However, many current automatic lip readi...
Uwe Meier, Rainer Stiefelhagen, Jie Yang, Alex Wai...
Abstract. In this pilot study, a neural architecture for temporal emotion recognition from image sequences is proposed. The investigation aims at the development of key principles ...