Deep learning has revolutionized many machine learning tasks in recent years, ranging
from image classification and video processing to speech recognition and natural language …

Lots of learning tasks require dealing with graph data which contains rich relation
information among elements. Modeling physics systems, learning molecular fingerprints …

Image-text matching has been a hot research topic bridging the vision and language areas.
It remains challenging because the current representation of image usually lacks global …

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 …

One of the most challenging question types in VQA is when answering the question requires
outside knowledge not present in the image. In this work we study open-domain knowledge …

We propose to compose dynamic tree structures that place the objects in an image into a
visual context, helping visual reasoning tasks such as scene graph generation and visual …

Scene graph is a structured representation of a scene that can clearly express the objects,
attributes, and relationships between objects in the scene. As computer vision technology …

Multimodal attentional networks are currently state-of-the-art models for Visual Question
Answering (VQA) tasks involving real images. Although attention allows to focus on the …

Automatic radiology report generation has been an attracting research problem towards
computer-aided diagnosis to alleviate the workload of doctors in recent years. Deep learning …

Similar to humans, RL agents use interactive learning to successfully obtain satisfactory
decision strategies. However, in many cases, it is desirable to learn directly from …