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 propose and address a new generalisation problem: can a model trained foraction recognition successfully classify actions when they are performed withina previously unseen scenario and in a previously unseen location? To answerthis question, we introduce the Action Recognition Generalisation Overscenarios and locations dataset (ARGO1M), which contains 1.1M video clips fromthe large-scale Ego4D dataset, across 10 scenarios and 13 locations. Wedemonstrate recognition models struggle to generalise over 10 proposed testsplits, each of an unseen scenario in an unseen location. We thus propose CIR,a method to represent each video as a Cross-Instance Reconstruction of videosfrom other domains. Reconstructions are paired with text narrations to guidethe learning of a domain generalisable representation. We provide extensiveanalysis and ablations on ARGO1M that show CIR outperforms prior domaingeneralisation works on all test splits. Code and data:https://chiaraplizz.github.io/what-can-a-cook/.

What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations