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

Answering semantically-complicated questions according to an image ischallenging in Visual Question Answering (VQA) task. Although the image can bewell represented by deep learning, the question is always simply embedded andcannot well indicate its meaning. Besides, the visual and textual features havea gap for different modalities, it is difficult to align and utilize thecross-modality information. In this paper, we focus on these two problems andpropose a Graph Matching Attention (GMA) network. Firstly, it not only buildsgraph for the image, but also constructs graph for the question in terms ofboth syntactic and embedding information. Next, we explore the intra-modalityrelationships by a dual-stage graph encoder and then present a bilateralcross-modality graph matching attention to infer the relationships between theimage and the question. The updated cross-modality features are then sent intothe answer prediction module for final answer prediction. Experimentsdemonstrate that our network achieves state-of-the-art performance on the GQAdataset and the VQA 2.0 dataset. The ablation studies verify the effectivenessof each modules in our GMA network.

Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering