Structured Query-Based Image Retrieval Using Scene Graphs

CVPRW 2020 pp. 680-684

doi:10.1109/CVPRW50498.2020.00097 /cvprw/2020/schroeder2020cvprw-structured/

Abstract

A structured query can capture the complexity of object interactions (e.g. ’woman rides motorcycle’) unlike single objects (e.g. ’woman’ or ’motorcycle’). Retrieval using structured queries therefore is much more useful than single object retrieval, but a much more challenging problem. In this paper we present a method which uses scene graph embeddings as the basis for an approach to image retrieval. We examine how visual relationships, derived from scene graphs, can be used as structured queries. The visual relationships are directed subgraphs of the scene graph with a subject and object as nodes connected by a predicate re-lationhship. Notably, we are able to achieve high recall even on low to medium frequency objects found in the long-tailed COCO-Stuff dataset, and find that adding a visual relationship-inspired loss boosts our recall by 10% in the best case.

PDF CVPRW Semantic Scholar

Cite

Text

Schroeder and Tripathi. "Structured Query-Based Image Retrieval Using Scene Graphs." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00097

Markdown

[Schroeder and Tripathi. "Structured Query-Based Image Retrieval Using Scene Graphs." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/schroeder2020cvprw-structured/) doi:10.1109/CVPRW50498.2020.00097

BibTeX

@inproceedings{schroeder2020cvprw-structured,
  title     = {{Structured Query-Based Image Retrieval Using Scene Graphs}},
  author    = {Schroeder, Brigit and Tripathi, Subarna},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {680-684},
  doi       = {10.1109/CVPRW50498.2020.00097},
  url       = {https://mlanthology.org/cvprw/2020/schroeder2020cvprw-structured/}
}