Joint Embeddings of Scene Graphs and Images

Eugene Belilovsky (1, 2, 3) , Matthew Blaschko (3) , Jamie Ryan Kiros (4) , Raquel Urtasun (4) , Richard Zemel (4)

1 CVN - Centre de vision numérique
2 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
3 Departement Elektrotechniek - ESAT [leuven]
4 University of Toronto

Multimodal representations of text and images have become popular in recent years. Text however has inherent ambiguities when describing visual scenes, leading to the recent development of datasets with detailed graphical descriptions in the form of scene graphs. We consider the task of joint representation of semantically precise scene graphs and images. We propose models for representing scene graphs and aligning them with images. We investigate methods based on bag-of-words, subpath representations, as well as neural networks. Our investigation proposes and contrasts several models which can address this task and highlights some unique challenges in both designing models and evaluation.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]

Eugene Belilovsky, Matthew Blaschko, Jamie Ryan Kiros, Raquel Urtasun, Richard Zemel. Joint Embeddings of Scene Graphs and Images. International Conference On Learning Representations - Workshop, 2017, Toulon, France. ⟨hal-01667777⟩