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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Unsupervised video object segmentation has made significant progress inrecent years, but the manual annotation of video mask datasets is expensive andlimits the diversity of available datasets. The Segment Anything Model (SAM)has introduced a new prompt-driven paradigm for image segmentation, unlocking arange of previously unexplored capabilities. In this paper, we propose a novelparadigm called UVOSAM, which leverages SAM for unsupervised video objectsegmentation without requiring video mask labels. To address SAM's limitationsin instance discovery and identity association, we introduce a video salientobject tracking network that automatically generates trajectories for prominentforeground objects. These trajectories then serve as prompts for SAM to producevideo masks on a frame-by-frame basis. Our experimental results demonstratethat UVOSAM significantly outperforms current mask-supervised methods. Thesefindings suggest that UVOSAM has the potential to improve unsupervised videoobject segmentation and reduce the cost of manual annotation.

UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model