Spatially Conditioned Graphs for Detecting Human-Object Interactions

Understand

We address the problem of detecting human-object interactions in images using graphical neural networks.

• Unlike conventional methods, where nodes send scaled but otherwise identical messages to each of their neighbours, we propose to condition messages between pairs of nodes on their spatial relationships, resulting in different messages going to neighbours of the same node.
• To this end, we explore various ways of applying spatial conditioning under a multi-branch structure.
• Through extensive experimentation we demonstrate the advantages of spatial conditioning for the computation of the adjacency structure, messages and the refined graph features.