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

Scene graph generation (SGG) aims to abstract an image into a graph structure, by
representing objects as graph nodes and their relations as labeled edges. However, two …

The uncertainty and dynamic of home environment present great challenges to the task
planning of service robots. The nature of the home environment is highly unstructured, with a …

We are living in a three-dimensional space while moving forward through a fourth
dimension: time. To allow artificial intelligence to develop a comprehensive understanding …

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

Embodied AI agents that search for objects in large environments such as households often
need to make efficient decisions by predicting object locations based on partial information …

Dynamic environments in factories, surgical robotics, and warehouses increasingly involve
humans, machines, robots, and various other objects such as tools, fixtures, conveyors, and …

Recent advances in metric, semantic, and topological mapping have equipped autonomous
robots with concept grounding capabilities to interpret natural language tasks. Leveraging …

Visual relationship detection aims to identify objects and their relationships in images. Prior
methods approach this task by adding separate relationship modules or decoders to existing …

Recent works have shown that Large Language Models (LLMs) can facilitate the grounding
of instructions for robotic task planning. Despite this progress, most existing works have …