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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We introduce a new task, visual sense disambiguation for verbs: given animage and a verb, assign the correct sense of the verb, i.e., the one thatdescribes the action depicted in the image. Just as textual word sensedisambiguation is useful for a wide range of NLP tasks, visual sensedisambiguation can be useful for multimodal tasks such as image retrieval,image description, and text illustration. We introduce VerSe, a new datasetthat augments existing multimodal datasets (COCO and TUHOI) with sense labels.We propose an unsupervised algorithm based on Lesk which performs visual sensedisambiguation using textual, visual, or multimodal embeddings. We find thattextual embeddings perform well when gold-standard textual annotations (objectlabels and image descriptions) are available, while multimodal embeddingsperform well on unannotated images. We also verify our findings by using thetextual and multimodal embeddings as features in a supervised setting andanalyse the performance of visual sense disambiguation task. VerSe is madepublicly available and can be downloaded at:https://github.com/spandanagella/verse.

Unsupervised Visual Sense Disambiguation for Verbs using Multimodal Embeddings