Skip to Main content Skip to Navigation
Poster communications

Joint Embeddings of Scene Graphs and Images

Abstract : 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.
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download
Contributor : Eugene Belilovsky Connect in order to contact the contributor
Submitted on : Tuesday, December 19, 2017 - 3:42:13 PM
Last modification on : Tuesday, May 3, 2022 - 3:14:04 PM


  • HAL Id : hal-01667777, version 1


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⟩



Record views


Files downloads