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

Spatial reasoning poses a particular challenge for intelligent agents and isat the same time a prerequisite for their successful interaction andcommunication in the physical world. One such reasoning task is to describe theposition of a target object with respect to the intrinsic orientation of somereference object via relative directions. In this paper, we introduceGRiD-A-3D, a novel diagnostic visual question-answering (VQA) dataset based onabstract objects. Our dataset allows for a fine-grained analysis of end-to-endVQA models' capabilities to ground relative directions. At the same time, modeltraining requires considerably fewer computational resources compared withexisting datasets, yet yields a comparable or even higher performance. Alongwith the new dataset, we provide a thorough evaluation based on two widelyknown end-to-end VQA architectures trained on GRiD-A-3D. We demonstrate thatwithin a few epochs, the subtasks required to reason over relative directions,such as recognizing and locating objects in a scene and estimating theirintrinsic orientations, are learned in the order in which relative directionsare intuitively processed.

Knowing Earlier what Right Means to You: A Comprehensive VQA Dataset for Grounding Relative Directions via Multi-Task Learning