preprintJul 1, 2017Closed access

Visual Translation Embedding Network for Visual Relation Detection

Columbia University · National University of Singapore

Indexed incrossref

Abstract

Visual relations, such as person ride bike and bike next to car, offer a comprehensive scene understanding of an image, and have already shown their great utility in connecting computer vision and natural language. However, due to the challenging combinatorial complexity of modeling subject-predicate-object relation triplets, very little work has been done to localize and predict visual relations. Inspired by the recent advances in relational representation learning of knowledge bases and convolutional object detection networks, we propose a Visual Translation Embedding network (VTransE) for visual relation detection. VTransE places objects in a low-dimensional relation space where a relation can be modeled as…

Citation impact

573
total citations
FWCI
25.41
Percentile
100%
References
59
Citations per year

Authors

4

Topics & keywords

Keywords
  • Computer science
  • Relation (database)
  • Artificial intelligence
  • Embedding
  • Inference
  • Relationship extraction
  • Spatial relation
  • Convolutional neural network
UN Sustainable Development Goals
  • Quality Education
No related works found for this paper.

Funding