A good image-to-image translation model should learn a mapping between different visual
domains while satisfying the following properties: 1) diversity of generated images and 2) …

The objective of this paper is' open-set'speaker recognition of unseen speakers, where ideal
embeddings should be able to condense information into a compact utterance-level …

Scene text detection methods based on neural networks have emerged recently and have
shown promising results. Previous methods trained with rigid word-level bounding boxes …

Motivation Biomedical text mining is becoming increasingly important as the number of
biomedical documents rapidly grows. With the progress in natural language processing …

Recent studies have demonstrated that gradient matching-based dataset synthesis, or
dataset condensation (DC), methods can achieve state-of-theart performance when applied …

Generative adversarial networks (GANs) synthesize realistic images from random latent
vectors. Although manipulating the latent vectors controls the synthesized outputs, editing …

Recent works in dialogue state tracking (DST) focus on an open vocabulary-based setting to
resolve scalability and generalization issues of the predefined ontology-based approaches …

Data augmentation is an effective way to improve the performance of deep networks.
Unfortunately, current methods are mostly developed for high-level vision tasks (eg …

This report describes our submission to the VoxCeleb Speaker Recognition Challenge
(VoxSRC) at Interspeech 2020. We perform a careful analysis of speaker recognition models …

Despite rapid advances in continual learning, a large body of research is devoted to
improving performance in the existing setups. While a handful of work do propose new …