We propose a novel scene graph generation model called Graph R-CNN, that is both effective and efficient at detecting objects and their relations in images.
#3 best model for Scene Graph Generation on Visual Genome
Statistical generative models for molecular graphs attract attention from many researchers from the fields of bio- and chemo-informatics.
We propose GraphNVP, the first invertible, normalizing flow-based molecular graph generation model.
Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry.
Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences.
We provide a new graph generator, based on a "forest fire" spreading process, that has a simple, intuitive justification, requires very few parameters (like the "flammability" of nodes), and produces graphs exhibiting the full range of properties observed both in prior work and in the present study.
Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e. g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach".
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 Q&A.
#2 best model for Scene Graph Generation on Visual Genome