Learning to Relate from Captions and Bounding Boxes

Sarthak Garg, Joel Ruben Antony Moniz, Anshu Aviral, Priyatham Bollimpalli


Abstract
In this work, we propose a novel approach that predicts the relationships between various entities in an image in a weakly supervised manner by relying on image captions and object bounding box annotations as the sole source of supervision. Our proposed approach uses a top-down attention mechanism to align entities in captions to objects in the image, and then leverage the syntactic structure of the captions to align the relations. We use these alignments to train a relation classification network, thereby obtaining both grounded captions and dense relationships. We demonstrate the effectiveness of our model on the Visual Genome dataset by achieving a recall@50 of 15% and recall@100 of 25% on the relationships present in the image. We also show that the model successfully predicts relations that are not present in the corresponding captions.
Anthology ID:
P19-1660
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6597–6603
Language:
URL:
https://aclanthology.org/P19-1660
DOI:
10.18653/v1/P19-1660
Bibkey:
Cite (ACL):
Sarthak Garg, Joel Ruben Antony Moniz, Anshu Aviral, and Priyatham Bollimpalli. 2019. Learning to Relate from Captions and Bounding Boxes. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6597–6603, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Learning to Relate from Captions and Bounding Boxes (Garg et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1660.pdf
Supplementary:
 P19-1660.Supplementary.pdf
Data
MS COCOVisual Genome