Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation

Zih Siou Hung, Arun Mallya, Svetlana Lazebnik

Research output: Contribution to journalArticlepeer-review

Abstract

Relations amongst entities play a central role in image understanding. Due to the complexity of modeling (subject, predicate, object) relation triplets, it is crucial to develop a method that can not only recognize seen relations, but also generalize to unseen cases. Inspired by a previously proposed visual translation embedding model, or VTransE [1] , we propose a context-augmented translation embedding model that can capture both common and rare relations. The previous VTransE model maps entities and predicates into a low-dimensional embedding vector space where the predicate is interpreted as a translation vector between the embedded features of the bounding box regions of the subject and the object. Our model additionally incorporates the contextual information captured by the bounding box of the union of the subject and the object, and learns the embeddings guided by the constraint predicate ≈ union (subject, object) - subject - object. In a comprehensive evaluation on multiple challenging benchmarks, our approach outperforms previous translation-based models and comes close to or exceeds the state of the art across a range of settings, from small-scale to large-scale datasets, from common to previously unseen relations. It also achieves promising results for the recently introduced task of scene graph generation.

Original languageEnglish (US)
Pages (from-to)3820-3832
Number of pages13
JournalIEEE transactions on pattern analysis and machine intelligence
Volume43
Issue number11
DOIs
StatePublished - Nov 1 2021

Keywords

  • Visual relationship detection
  • scene graph generation
  • scene understanding

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Applied Mathematics
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation'. Together they form a unique fingerprint.

Cite this