Published in arXiv: Computer Science: Computer Vision and Pattern Recognition, 2019
This paper introduces a novel few-shot capable Scene Graph Prediction model, which applies Graph Convolution Networks to learn a relationship-oriented embedding space for objects in the scene.
Recommended citation: Apoorva Dornadula, Austin Narcomey, Ranjay Krishna, Michael Bernstein, Li Fei-Fei. "Learning Object Representationswith Predicate Functions: Enabling Few-Shot Scene Graph Prediction." arXiv. 2019. https://arxiv.org/abs/1906.04876