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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

One of the biggest challenges in Multimedia information retrieval andunderstanding is to bridge the semantic gap by properly modeling conceptsemantics in context. The presence of out of vocabulary (OOV) conceptsexacerbates this difficulty. To address the semantic gap issues, we formulate aproblem on learning contextualized semantics from descriptive terms and proposea novel Siamese architecture to model the contextualized semantics fromdescriptive terms. By means of pattern aggregation and probabilistic topicmodels, our Siamese architecture captures contextualized semantics from theco-occurring descriptive terms via unsupervised learning, which leads to aconcept embedding space of the terms in context. Furthermore, the co-occurringOOV concepts can be easily represented in the learnt concept embedding space.The main properties of the concept embedding space are demonstrated viavisualization. Using various settings in semantic priming, we have carried outa thorough evaluation by comparing our approach to a number of state-of-the-artmethods on six annotation corpora in different domains, i.e., MagTag5K, CAL500and Million Song Dataset in the music domain as well as Corel5K, LabelMe andSUNDatabase in the image domain. Experimental results on semantic primingsuggest that our approach outperforms those state-of-the-art methodsconsiderably in various aspects.

Learning Contextualized Semantics from Co-occurring Terms via a Siamese Architecture