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

We consider the problem of Vision-and-Language Navigation (VLN). The majorityof current methods for VLN are trained end-to-end using either unstructuredmemory such as LSTM, or using cross-modal attention over the egocentricobservations of the agent. In contrast to other works, our key insight is thatthe association between language and vision is stronger when it occurs inexplicit spatial representations. In this work, we propose a cross-modal maplearning model for vision-and-language navigation that first learns to predictthe top-down semantics on an egocentric map for both observed and unobservedregions, and then predicts a path towards the goal as a set of waypoints. Inboth cases, the prediction is informed by the language through cross-modalattention mechanisms. We experimentally test the basic hypothesis thatlanguage-driven navigation can be solved given a map, and then show competitiveresults on the full VLN-CE benchmark.

Cross-modal Map Learning for Vision and Language Navigation