Paying Attention to Descriptions Generated by Image Captioning Models

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Researchers

Research units

  • Max Planck Institute for Informatics
  • University of Central Florida

Abstract

To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene. In this paper, we study the agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs. We investigate the properties of human-written descriptions and machine-generated ones. We then propose a saliency-boosted image captioning model in order to investigate benefits from low-level cues in language models. We learn that (1) humans mention more salient objects earlier than less salient ones in their descriptions, (2) the better a captioning model performs, the better attention agreement it has with human descriptions, (3) the proposed saliencyboosted model, compared to its baseline form, does not improve significantly on the MS COCO database, indicating explicit bottom-up boosting does not help when the task is well learnt and tuned on a data, (4) a better generalization is, however, observed for the saliency-boosted model on unseen data.

Details

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
Publication statusPublished - 2017
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Computer Vision - Venice, Italy
Duration: 22 Oct 201729 Oct 2017

Publication series

NameIEEE International Conference on Computer Vision
PublisherIEEE
ISSN (Print)1550-5499
ISSN (Electronic)2380-7504

Conference

ConferenceInternational Conference on Computer Vision
Abbreviated titleICCV
CountryItaly
CityVenice
Period22/10/201729/10/2017

    Research areas

  • Visualization, Measurement, Data models, Grammar, Computational modeling, Computer science

Download statistics

No data available

ID: 14436314