Image Description using Visual Dependency Representations

Desmond Elliott, Frank Keller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Describing the main event of an image involves
identifying the objects depicted and
predicting the relationships between them.
Previous approaches have represented images
as unstructured bags of regions, which makes
it difficult to accurately predict meaningful
relationships between regions. In this paper,
we introduce visual dependency representations
to capture the relationships between
the objects in an image, and hypothesize that
this representation can improve image description.
We test this hypothesis using a
new data set of region-annotated images, associated
with visual dependency representations
and gold-standard descriptions. We describe
two template-based description generation
models that operate over visual dependency
representations. In an image description
task, we find that these models outperform
approaches that rely on object proximity
or corpus information to generate descriptions
on both automatic measures and on human
judgements.
Original languageEnglish
Title of host publicationProceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, 18-21 October 2013, Grand Hyatt Seattle, Seattle, Washington, USA, A meeting of SIGDAT, a Special Interest Group of the ACL
Pages1292-1302
Number of pages11
Publication statusPublished - Oct 2013

Fingerprint Dive into the research topics of 'Image Description using Visual Dependency Representations'. Together they form a unique fingerprint.

Cite this