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

Visual Commonsense Reasoning (VCR) remains a significant yet challengingresearch problem in the realm of visual reasoning. A VCR model generally aimsat answering a textual question regarding an image, followed by the rationaleprediction for the preceding answering process. Though these two processes aresequential and intertwined, existing methods always consider them as twoindependent matching-based instances. They, therefore, ignore the pivotalrelationship between the two processes, leading to sub-optimal modelperformance. This paper presents a novel visual attention alignment method toefficaciously handle these two processes in a unified framework. To achievethis, we first design a re-attention module for aggregating the visionattention map produced in each process. Thereafter, the resultant two sets ofattention maps are carefully aligned to guide the two processes to makedecisions based on the same image regions. We apply this method to bothconventional attention and the recent Transformer models and carry outextensive experiments on the VCR benchmark dataset. The results demonstratethat with the attention alignment module, our method achieves a considerableimprovement over the baseline methods, evidently revealing the feasibility ofthe coupling of the two processes as well as the effectiveness of the proposedmethod.

Learning to Agree on Vision Attention for Visual Commonsense Reasoning