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

Advances in deep learning have enabled the development of models that haveexhibited a remarkable tendency to recognize and even localize actions invideos. However, they tend to experience errors when faced with scenes orexamples beyond their initial training environment. Hence, they fail to adaptto new domains without significant retraining with large amounts of annotateddata. In this paper, we propose to overcome these limitations by moving to anopen-world setting by decoupling the ideas of recognition and reasoning.Building upon the compositional representation offered by Grenander's PatternTheory formalism, we show that attention and commonsense knowledge can be usedto enable the self-supervised discovery of novel actions in egocentric videosin an open-world setting, where data from the observed environment (the targetdomain) is open i.e., the vocabulary is partially known and training examples(both labeled and unlabeled) are not available. We show that our approach caninfer and learn novel classes for open vocabulary classification in egocentricvideos and novel object detection with zero supervision. Extensive experimentsshow its competitive performance on two publicly available egocentric actionrecognition datasets (GTEA Gaze and GTEA Gaze+) under open-world conditions.

Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision