In the last few years, a large number of automatic evaluation metrics have been proposed for
evaluating Natural Language Generation (NLG) systems. The rapid development and …

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 …

Existing research addresses scene graph generation (SGG)—a critical technology for scene
understanding in images—from a detection perspective, ie., objects are detected using …

A creative idea is often born from transforming, combining, and modifying ideas from existing
visual examples capturing various concepts. However, one cannot simply copy the concept …

Reasoning over visual data is a desirable capability for robotics and vision-based
applications. Such reasoning enables forecasting the next events or actions in videos. In …

Image captioning which automatically generates natural language descriptions for images
has attracted lots of research attentions and there have been substantial progresses with …

Humans can not only see the collection of objects in visual scenes, but also identify the
relationship between objects. The visual relationship in the scene can be abstracted into the …

3D spatial perception is the problem of building and maintaining an actionable and
persistent representation of the environment in real-time using sensor data and prior …

Within the realm of service robotics, researchers have placed a great amount of effort into
learning, understanding, and representing motions as manipulations for task execution by …

Abstract Panoptic Scene Graph has recently been proposed for comprehensive scene
understanding. However, previous works adopt a fully-supervised learning manner …