Despite their success, deep networks are used as black-box models with outputs that are not
easily explainable during the learning and the prediction phases. This lack of interpretability …

A long time ago in the machine learning literature, the idea of incorporating a mechanism
inspired by the human visual system into neural networks was introduced. This idea is …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Recent methods for visual question answering rely on large-scale annotated datasets.
Manual annotation of questions and answers for videos, however, is tedious, expensive and …

Few-shot classification aims to recognize unlabeled samples from unseen classes given
only few labeled samples. The unseen classes and low-data problem make few-shot …

Abstract Visual Question Answering (VQA) in its ideal form lets us study reasoning in the
joint space of vision and language and serves as a proxy for the AI task of scene …

Saliency detection is one of the basic challenges in computer vision. Recently, CNNs are the
most widely used and powerful techniques for saliency detection, in which feature maps …

Studies have shown that a dominant class of questions asked by visually impaired users on
images of their surroundings involves reading text in the image. But today's VQA models can …

In humans, Attention is a core property of all perceptual and cognitive operations. Given our
limited ability to process competing sources, attention mechanisms select, modulate, and …

Generating an image from a given text description has two goals: visual realism and
semantic consistency. Although significant progress has been made in generating high …