Abstract The Visual Genome Dataset is the de facto standard dataset used in Scene Graph
generation. It contains a large collection of images with corresponding object and …

Textbook Question Answering (TQA) is the task of answering diagram and non-diagram
questions given large multi-modal contexts consisting of abundant text and diagrams. Deep …

Scene Graph Generation (SGG), given an image, is the task of building directed graphs
where edges represent predicted triplets. Most SGG models struggle to identify important …

Visual commonsense contains knowledge about object properties, relationships, and
behaviors in visual data. Discovering visual commonsense can provide a more …

Visual and spatial relationship detection in images has been a fast-developing research
topic in the multimedia field, which learns to recognize the semantic/spatial interactions …

Machine learning model bias can arise from dataset composition: sensitive features
correlated to the learning target disturb the model decision rule and lead to performance …

Visual relations are complex, multimodal concepts that play an important role in the way
humans perceive the world. As a result of their complexity, high-quality, diverse and large …

Deep learning and data-driven approaches are commonly used to avoid accidents involving
elders and children. However, existing models are limited by a semantic gap, hindering their …

Modern approaches to scene graph generation still struggle with their performance, with
even state of the art approaches hovering under a 15% mean recall on certain evaluation …

Deep learning has dominated the landscape of computer vision for the past decade. Deep
learning networks are the top performers on a slew of computer vision challenges (eg, object …