We focus on the confounding bias between language and location in the visual grounding
pipeline, where we find that the bias is the major visual reasoning bottleneck. For example …

Referring expression comprehension and segmentation aim to locate and segment a
referred instance in an image according to a natural language expression. However …

When interacting with objects through cameras, or pictures, users often have a specific
intent. For example, they may want to perform a visual search. With most object detection …

Deep learning has delivered its powerfulness in many application domains, especially in
computer vision, natural language processing and speech recognition. As the backbone of …