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 …

A graph structure is a powerful mathematical abstraction, which can not only represent
information about individuals but also capture the interactions between individuals for …

Abstract Vision-Language Pre-training (VLP) models have shown promising capabilities in
grounding natural language in image data, facilitating a broad range of cross-modal tasks …

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

Today's scene graph generation (SGG) task is still far from practical, mainly due to the
severe training bias, eg, collapsing diverse" human walk on/sit on/lay on beach" into" human …

Adapter-style efficient transfer learning (ETL) has shown excellent performance in the tuning
of vision-language models (VLMs) under the low-data regime, where only a few additional …

Scene graph generation is an important visual understanding task with a broad range of
vision applications. Despite recent tremendous progress, it remains challenging due to the …

Deep learning on graphs has become one of the hottest topics in machine learning. The
book consists of four parts to best accommodate our readers with diverse backgrounds and …

Abstract Knowledge-based visual question answering requires the ability of associating
external knowledge for open-ended cross-modal scene understanding. One limitation of …

Unbiased SGG has achieved significant progress over recent years. However, almost all
existing SGG models have overlooked the ground-truth annotation qualities of prevailing …