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

Recently, the Visual Question Answering (VQA) task has gained increasingattention in artificial intelligence. Existing VQA methods mainly adopt thevisual attention mechanism to associate the input question with correspondingimage regions for effective question answering. The free-form region based andthe detection-based visual attention mechanisms are mostly investigated, withthe former ones attending free-form image regions and the latter ones attendingpre-specified detection-box regions. We argue that the two attention mechanismsare able to provide complementary information and should be effectivelyintegrated to better solve the VQA problem. In this paper, we propose a noveldeep neural network for VQA that integrates both attention mechanisms. Ourproposed framework effectively fuses features from free-form image regions,detection boxes, and question representations via a multi-modal multiplicativefeature embedding scheme to jointly attend question-related free-form imageregions and detection boxes for more accurate question answering. The proposedmethod is extensively evaluated on two publicly available datasets, COCO-QA andVQA, and outperforms state-of-the-art approaches. Source code is available athttps://github.com/lupantech/dual-mfa-vqa.

Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question Answering