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

Since first proposed, Video Instance Segmentation(VIS) task has attractedvast researchers' focus on architecture modeling to boost performance. Thoughgreat advances achieved in online and offline paradigms, there are stillinsufficient means to identify model errors and distinguish discrepanciesbetween methods, as well approaches that correctly reflect models' performancein recognizing object instances of various temporal lengths remain barelyavailable. More importantly, as the fundamental model abilities demanded by thetask, spatial segmentation and temporal association are still understudied inboth evaluation and interaction mechanisms. In this paper, we introduce TIVE, aToolbox for Identifying Video instance segmentation Errors. By directlyoperating output prediction files, TIVE defines isolated error types andweights each type's damage to mAP, for the purpose of distinguishing modelcharacters. By decomposing localization quality in spatial-temporal dimensions,model's potential drawbacks on spatial segmentation and temporal associationcan be revealed. TIVE can also report mAP over instance temporal length forreal applications. We conduct extensive experiments by the toolbox to furtherillustrate how spatial segmentation and temporal association affect each other.We expect the analysis of TIVE can give the researchers more insights, guidingthe community to promote more meaningful explorations for video instancesegmentation. The proposed toolbox is available athttps://github.com/wenhe-jia/TIVE.

TIVE: A Toolbox for Identifying Video Instance Segmentation Errors