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

This paper introduces a two-phase deep feature engineering framework forefficient learning of semantics enhanced joint embedding, which clearlyseparates the deep feature engineering in data preprocessing from training thetext-image joint embedding model. We use the Recipe1M dataset for the technicaldescription and empirical validation. In preprocessing, we perform deep featureengineering by combining deep feature engineering with semantic contextfeatures derived from raw text-image input data. We leverage LSTM to identifykey terms, deep NLP models from the BERT family, TextRank, or TF-IDF to produceranking scores for key terms before generating the vector representation foreach key term by using word2vec. We leverage wideResNet50 and word2vec toextract and encode the image category semantics of food images to help semanticalignment of the learned recipe and image embeddings in the joint latent space.In joint embedding learning, we perform deep feature engineering by optimizingthe batch-hard triplet loss function with soft-margin and double negativesampling, taking into account also the category-based alignment loss anddiscriminator-based alignment loss. Extensive experiments demonstrate that ourSEJE approach with deep feature engineering significantly outperforms thestate-of-the-art approaches.

Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering