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

Multimodal learning from document data has achieved great success lately asit allows to pre-train semantically meaningful features as a prior into alearnable downstream task. In this paper, we approach the documentclassification problem by learning cross-modal representations through languageand vision cues, considering intra- and inter-modality relationships. Insteadof merging features from different modalities into a joint representationspace, the proposed method exploits high-level interactions and learns relevantsemantic information from effective attention flows within and acrossmodalities. The proposed learning objective is devised between intra- andinter-modality alignment tasks, where the similarity distribution per task iscomputed by contracting positive sample pairs while simultaneously contrastingnegative ones in the joint representation space}. Extensive experiments onpublic document classification datasets demonstrate the effectiveness and thegenerality of our model on low-scale and large-scale datasets.

VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification