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

Cross-modal representation learning learns a shared embedding between two ormore modalities to improve performance in a given task compared to using onlyone of the modalities. Cross-modal representation learning from different datatypes -- such as images and time-series data (e.g., audio or text data) --requires a deep metric learning loss that minimizes the distance between themodality embeddings. In this paper, we propose to use the contrastive ortriplet loss, which uses positive and negative identities to create samplepairs with different labels, for cross-modal representation learning betweenimage and time-series modalities (CMR-IS). By adapting the triplet loss forcross-modal representation learning, higher accuracy in the main (time-seriesclassification) task can be achieved by exploiting additional information ofthe auxiliary (image classification) task. We present a triplet loss with adynamic margin for single label and sequence-to-sequence classification tasks.We perform extensive evaluations on synthetic image and time-series data, andon data for offline handwriting recognition (HWR) and on online HWR fromsensor-enhanced pens for classifying written words. Our experiments show animproved classification accuracy, faster convergence, and bettergeneralizability due to an improved cross-modal representation. Furthermore,the more suitable generalizability leads to a better adaptability betweenwriters for online HWR.

Auxiliary Cross-Modal Representation Learning with Triplet Loss Functions for Online Handwriting Recognition