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

Exploring dense matching between the current frame and past frames forlong-range context modeling, memory-based methods have demonstrated impressiveresults in video object segmentation (VOS) recently. Nevertheless, due to thelack of instance understanding ability, the above approaches are oftentimesbrittle to large appearance variations or viewpoint changes resulted from themovement of objects and cameras. In this paper, we argue that instanceunderstanding matters in VOS, and integrating it with memory-based matching canenjoy the synergy, which is intuitively sensible from the definition of VOStask, \ie, identifying and segmenting object instances within the video.Towards this goal, we present a two-branch network for VOS, where thequery-based instance segmentation (IS) branch delves into the instance detailsof the current frame and the VOS branch performs spatial-temporal matching withthe memory bank. We employ the well-learned object queries from IS branch toinject instance-specific information into the query key, with which theinstance-augmented matching is further performed. In addition, we introduce amulti-path fusion block to effectively combine the memory readout withmulti-scale features from the instance segmentation decoder, which incorporateshigh-resolution instance-aware features to produce final segmentation results.Our method achieves state-of-the-art performance on DAVIS 2016/2017 val (92.6%and 87.1%), DAVIS 2017 test-dev (82.8%), and YouTube-VOS 2018/2019 val (86.3%and 86.3%), outperforming alternative methods by clear margins.

Look Before You Match: Instance Understanding Matters in Video Object Segmentation