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

Multi-modal keyphrase generation aims to produce a set of keyphrases thatrepresent the core points of the input text-image pair. In this regard,dominant methods mainly focus on multi-modal fusion for keyphrase generation.Nevertheless, there are still two main drawbacks: 1) only a limited number ofsources, such as image captions, can be utilized to provide auxiliaryinformation. However, they may not be sufficient for the subsequent keyphrasegeneration. 2) the input text and image are often not perfectly matched, andthus the image may introduce noise into the model. To address theselimitations, in this paper, we propose a novel multi-modal keyphrase generationmodel, which not only enriches the model input with external knowledge, butalso effectively filters image noise. First, we introduce external visualentities of the image as the supplementary input to the model, which benefitsthe cross-modal semantic alignment for keyphrase generation. Second, wesimultaneously calculate an image-text matching score and image region-textcorrelation scores to perform multi-granularity image noise filtering.Particularly, we introduce the correlation scores between image regions andground-truth keyphrases to refine the calculation of the previously-mentionedcorrelation scores. To demonstrate the effectiveness of our model, we conductseveral groups of experiments on the benchmark dataset.  Experimental results and in-depth analyses show that our model achieves thestate-of-the-art performance. Our code is available onhttps://github.com/DeepLearnXMU/MM-MKP.

Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering