Despite being extensively studied in the literature, the problem of gender recognition from face images remains difficult when dealing with unconstrained images in a cross-dataset...
Many students use videos to supplement learning outside the classroom. This is particularly important for students with challenged visual capacities, for whom seeing the board dur...
Text detection and recognition in video is challenging due to the presence of different types of texts, namely, graphics (video caption), scene (natural text), 2D, 3D, static and ...
Mislabeled examples in the training data can severely affect the performance of supervised classifiers. In this paper, we present an approach to remove any mislabeled examples i...
Ekambaram Rajmadhan, Sergiy Fefilatyev, Matthew Sh...