Deep Learning and its applications have cascaded impactful research and development
with a diverse range of modalities present in the real-world data. More recently, this has …

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 …

Top-down visual attention mechanisms have been used extensively in image captioning
and visual question answering (VQA) to enable deeper image understanding through fine …

The multimodal task of Visual Question Answering (VQA) encompassing elements of
Computer Vision (CV) and Natural Language Processing (NLP), aims to generate answers …

A number of studies have found that today's Visual Question Answering (VQA) models are
heavily driven by superficial correlations in the training data and lack sufficient image …

Visual grounding, ie, localizing objects in images according to natural language queries, is
an important topic in visual language understanding. The most effective approaches for this …

Sketch-based image retrieval (SBIR) is the task of retrieving images from a natural image
database that correspond to a given hand-drawn sketch. Ideally, an SBIR model should …

Visual Question Answering (VQA) has benefited from increasingly sophisticated models, but
has not enjoyed the same level of engagement in terms of data creation. In this paper, we …

While progress has been made on the visual question answering leaderboards, models
often utilize spurious correlations and priors in datasets under the iid setting. As such …

One of the primary challenges limiting the applicability of deep learning is its susceptibility to
learning spurious correlations rather than the underlying mechanisms of the task of interest …