Visual question answering requires high-order reasoning about an image, which is a
fundamental capability needed by machine systems to follow complex directives. Recently …

When building artificial intelligence systems that can reason and answer questions about
visual data, we need diagnostic tests to analyze our progress and discover short-comings …

We present a novel framework for iterative visual reasoning. Our framework goes beyond
current recognition systems that lack the capability to reason beyond stack of convolutions …

Dramatic progress has been witnessed in basic vision tasks involving low-level perception,
such as object recognition, detection, and tracking. Unfortunately, there is still enormous …

We aim to dismantle the prevalent black-box neural architectures used in complex visual
reasoning tasks, into the proposed eXplainable and eXplicit Neural Modules (XNMs), which …

Existing explainable and explicit visual reasoning methods only perform reasoning based
on visual evidence but do not take into account knowledge beyond what is in the visual …

Existing methods for visual reasoning attempt to directly map inputs to outputs using black-
box architectures without explicitly modeling the underlying reasoning processes. As a …

Despite substantial progress in applying neural networks (NN) to a wide variety of areas,
they still largely suffer from a lack of transparency and interpretability. While recent …

Visual question answering is fundamentally compositional in nature---a question like" where
is the dog?" shares substructure with questions like" what color is the dog?" and" where is …

Visual Question answering is a challenging problem requiring a combination of concepts
from Computer Vision and Natural Language Processing. Most existing approaches use a …