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

Vision and language navigation (VLN) is a challenging visually-groundedlanguage understanding task. Given a natural language navigation instruction, avisual agent interacts with a graph-based environment equipped with panoramaimages and tries to follow the described route. Most prior work has beenconducted in indoor scenarios where best results were obtained for navigationon routes that are similar to the training routes, with sharp drops inperformance when testing on unseen environments. We focus on VLN in outdoorscenarios and find that in contrast to indoor VLN, most of the gain in outdoorVLN on unseen data is due to features like junction type embedding or headingdelta that are specific to the respective environment graph, while imageinformation plays a very minor role in generalizing VLN to unseen outdoorareas. These findings show a bias to specifics of graph representations ofurban environments, demanding that VLN tasks grow in scale and diversity ofgeographical environments.

Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas