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

Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novelcompositions of state and object primitives in images with no priors on thecompositional space, which induces a tremendously large output space containingall possible state-object compositions. Existing works either learn the jointcompositional state-object embedding or predict simple primitives with separateclassifiers. However, the former heavily relies on external word embeddingmethods, and the latter ignores the interactions of interdependent primitives,respectively. In this paper, we revisit the primitive prediction approach andpropose a novel method, termed Progressive Cross-primitive Compatibility(ProCC), to mimic the human learning process for OW-CZSL tasks. Specifically,the cross-primitive compatibility module explicitly learns to model theinteractions of state and object features with the trainable memory units,which efficiently acquires cross-primitive visual attention to reasonhigh-feasibility compositions, without the aid of external knowledge. Moreover,considering the partial-supervision setting (pCZSL) as well as the imbalanceissue of multiple task prediction, we design a progressive training paradigm toenable the primitive classifiers to interact to obtain discriminativeinformation in an easy-to-hard manner. Extensive experiments on three widelyused benchmark datasets demonstrate that our method outperforms otherrepresentative methods on both OW-CZSL and pCZSL settings by large margins.

ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning