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

The Associating Objects with Transformers (AOT) framework has exhibitedexceptional performance in a wide range of complex scenarios for video objectsegmentation. In this study, we introduce MSDeAOT, a variant of the AOT seriesthat incorporates transformers at multiple feature scales. Leveraging thehierarchical Gated Propagation Module (GPM), MSDeAOT efficiently propagatesobject masks from previous frames to the current frame using a feature scalewith a stride of 16. Additionally, we employ GPM in a more refined featurescale with a stride of 8, leading to improved accuracy in detecting andtracking small objects. Through the implementation of test-time augmentationsand model ensemble techniques, we achieve the top-ranking position in theEPIC-KITCHEN VISOR Semi-supervised Video Object Segmentation Challenge.

ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: Semi-Supervised Video Object Segmentation