Paying Attention to Descriptions Generated by Image Captioning Models

Loading...
Thumbnail Image
Journal Title
Journal ISSN
Volume Title
Conference article in proceedings
Date
2017
Major/Subject
Mcode
Degree programme
Language
en
Pages
2506-2515
Series
2017 IEEE International Conference on Computer Vision (ICCV), IEEE International Conference on Computer Vision
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.
Description
Keywords
Visualization, Measurement, Data models, Grammar, Computational modeling, Computer science
Other note
Citation
Rezazadegan Tavakoli, H, Shetty, R, Borji, A & Laaksonen, J 2017, Paying Attention to Descriptions Generated by Image Captioning Models . in Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017 ., 8237534, IEEE International Conference on Computer Vision, IEEE, pp. 2506-2515, IEEE International Conference on Computer Vision, Venice, Italy, 22/10/2017 . https://doi.org/10.1109/ICCV.2017.272