Indeed, as we demonstrate, their performance degrades significantly for larger molecules.
Extracting graph representation of visual scenes in image is a challenging task in computer vision.
Graph generation with Machine Learning is an open problem with applications in various research fields.
The abundance of interconnected data has fueled the design and implementation of graph generators reproducing real-world linking properties, or gauging the effectiveness of graph algorithms, techniques and applications manipulating these data.
Finally, we propose the first graph-based weakly supervised learning framework based on a novel graph alignment algorithm, which enables training without bounding box annotations.
Based on this new perspective, we re-formulate scene graph generation as the inference of a bridge between the scene and commonsense graphs, where each entity or predicate instance in the scene graph has to be linked to its corresponding entity or predicate class in the commonsense graph.