VSGNet

2000년 도입 · 논문 1편에서 사용

Visual-Spatial-Graph Network (VSGNet) is a network for human-object interaction detection. It extracts visual features from the image representing the human-object pair, refines the features with spatial configurations of the pair, and utilizes the structural connections between the pair via graph convolutions.

출처: VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions

소개 논문: VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions