Learning to Select: A Fully Attentive Approach for Novel Object Captioning

Abstract: Image captioning models have lately shown impressive results when applied to standard datasets. Switching to real-life scenarios, however, constitutes a challenge due to the larger variety of visual concepts which are not covered in existing training sets. For this reason, novel object captioning (NOC) has recently emerged as a paradigm to test captioning models on objects which are unseen during the training phase. In this paper, we present a novel approach for NOC that learns to select the most relevant objects of an image, regardless of their adherence to the training set, and to constrain the generative process of a language model accordingly. Our architecture is fully-attentive and end-to-end trainable, also when incorporating constraints. We perform experiments on the held-out COCO dataset, where we demonstrate improvements over the state of the art, both in terms of adaptability to novel objects and caption quality.

Citation:

Cagrandi, Marco; Cornia, Marcella; Stefanini, Matteo; Baraldi, Lorenzo; Cucchiara, Rita "Learning to Select: A Fully Attentive Approach for Novel Object Captioning" Proceedings of the ACM International Conference on Multimedia Retrieval, Taipei, Taiwan, pp. 437 -441 , August 21-24, 2021, 2021 DOI: 10.1145/3460426.3463587

 not available

Paper download:

• Author version:
• DOI: 10.1145/3460426.3463587