English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Image captioning models have lately shown impressive results when applied tostandard datasets. Switching to real-life scenarios, however, constitutes achallenge due to the larger variety of visual concepts which are not covered inexisting training sets. For this reason, novel object captioning (NOC) hasrecently emerged as a paradigm to test captioning models on objects which areunseen during the training phase. In this paper, we present a novel approachfor NOC that learns to select the most relevant objects of an image, regardlessof their adherence to the training set, and to constrain the generative processof a language model accordingly. Our architecture is fully-attentive andend-to-end trainable, also when incorporating constraints. We performexperiments on the held-out COCO dataset, where we demonstrate improvementsover the state of the art, both in terms of adaptability to novel objects andcaption quality.

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