TY - GEN
T1 - Language-Driven Region Pointer Advancement for Controllable Image Captioning
AU - Lindh, Annika
AU - Ross, Robert
AU - Kelleher, John D.
N1 - Publisher Copyright:
© 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.
PY - 2020
Y1 - 2020
N2 - Controllable Image Captioning is a recent sub-field in the multi-modal task of Image Captioning wherein constraints are placed on which regions in an image should be described in the generated natural language caption. This puts a stronger focus on producing more detailed descriptions, and opens the door for more end-user control over results. A vital component of the Controllable Image Captioning architecture is the mechanism that decides the timing of attending to each region through the advancement of a region pointer. In this paper, we propose a novel method for predicting the timing of region pointer advancement by treating the advancement step as a natural part of the language structure via a NEXT-token, motivated by a strong correlation to the sentence structure in the training data. We find that our timing agrees with the ground-truth timing in the Flickr30k Entities test data with a precision of 86.55% and a recall of 97.92%. Our model implementing this technique improves the state-of-the-art on standard captioning metrics while additionally demonstrating a considerably larger effective vocabulary size.
AB - Controllable Image Captioning is a recent sub-field in the multi-modal task of Image Captioning wherein constraints are placed on which regions in an image should be described in the generated natural language caption. This puts a stronger focus on producing more detailed descriptions, and opens the door for more end-user control over results. A vital component of the Controllable Image Captioning architecture is the mechanism that decides the timing of attending to each region through the advancement of a region pointer. In this paper, we propose a novel method for predicting the timing of region pointer advancement by treating the advancement step as a natural part of the language structure via a NEXT-token, motivated by a strong correlation to the sentence structure in the training data. We find that our timing agrees with the ground-truth timing in the Flickr30k Entities test data with a precision of 86.55% and a recall of 97.92%. Our model implementing this technique improves the state-of-the-art on standard captioning metrics while additionally demonstrating a considerably larger effective vocabulary size.
UR - http://www.scopus.com/inward/record.url?scp=85103808581&partnerID=8YFLogxK
U2 - 10.18653/v1/2020.coling-main.174
DO - 10.18653/v1/2020.coling-main.174
M3 - Conference contribution
AN - SCOPUS:85103808581
T3 - COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference
SP - 1922
EP - 1935
BT - COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference
A2 - Scott, Donia
A2 - Bel, Nuria
A2 - Zong, Chengqing
PB - Association for Computational Linguistics (ACL)
T2 - 28th International Conference on Computational Linguistics, COLING 2020
Y2 - 8 December 2020 through 13 December 2020
ER -