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

Recent works have shown that objects discovery can largely benefit from theinherent motion information in video data. However, these methods lack a properbackground processing, resulting in an over-segmentation of the non-objectregions into random segments. This is a critical limitation given theunsupervised setting, where object segments and noise are not distinguishable.To address this limitation we propose BMOD, a Background-aware Motion-guidedObjects Discovery method. Concretely, we leverage masks of moving objectsextracted from optical flow and design a learning mechanism to extend them tothe true foreground composed of both moving and static objects. The background,a complementary concept of the learned foreground class, is then isolated inthe object discovery process. This enables a joint learning of the objectsdiscovery task and the object/non-object separation. The conducted experimentson synthetic and real-world datasets show that integrating our backgroundhandling with various cutting-edge methods brings each time a considerableimprovement. Specifically, we improve the objects discovery performance with alarge margin, while establishing a strong baseline for object/non-objectseparation.

The Background Also Matters: Background-Aware Motion-Guided Objects Discovery