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

Segmentation and tracking of unseen object instances in discrete frames posea significant challenge in dynamic industrial robotic contexts, such asdistribution warehouses. Here, robots must handle object rearrangement,including shifting, removal, and partial occlusion by new items, and trackthese items after substantial temporal gaps. The task is further complicatedwhen robots encounter objects not learned in their training sets, whichrequires the ability to segment and track previously unseen items. Consideringthat continuous observation is often inaccessible in such settings, our taskinvolves working with a discrete set of frames separated by indefinite periodsduring which substantial changes to the scene may occur. This task alsotranslates to domestic robotic applications, such as rearrangement of objectson a table. To address these demanding challenges, we introduce new syntheticand real-world datasets that replicate these industrial and householdscenarios. We also propose a novel paradigm for joint segmentation and trackingin discrete frames along with a transformer module that facilitates efficientinter-frame communication. The experiments we conduct show that our approachsignificantly outperforms recent methods. For additional results and videos,please visit \href{https://sites.google.com/view/stow-corl23}{website}. Codeand dataset will be released.

STOW: Discrete-Frame Segmentation and Tracking of Unseen Objects for Warehouse Picking Robots