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

Video instance segmentation (VIS) is a critical task with diverseapplications, including autonomous driving and video editing. Existing methodsoften underperform on complex and long videos in real world, primarily due totwo factors. Firstly, offline methods are limited by the tightly-coupledmodeling paradigm, which treats all frames equally and disregards theinterdependencies between adjacent frames. Consequently, this leads to theintroduction of excessive noise during long-term temporal alignment. Secondly,online methods suffer from inadequate utilization of temporal information. Totackle these challenges, we propose a decoupling strategy for VIS by dividingit into three independent sub-tasks: segmentation, tracking, and refinement.The efficacy of the decoupling strategy relies on two crucial elements: 1)attaining precise long-term alignment outcomes via frame-by-frame associationduring tracking, and 2) the effective utilization of temporal informationpredicated on the aforementioned accurate alignment outcomes during refinement.We introduce a novel referring tracker and temporal refiner to construct the\textbf{D}ecoupled \textbf{VIS} framework (\textbf{DVIS}). DVIS achieves newSOTA performance in both VIS and VPS, surpassing the current SOTA methods by7.3 AP and 9.6 VPQ on the OVIS and VIPSeg datasets, which are the mostchallenging and realistic benchmarks. Moreover, thanks to the decouplingstrategy, the referring tracker and temporal refiner are super light-weight(only 1.69\% of the segmenter FLOPs), allowing for efficient training andinference on a single GPU with 11G memory. The code is available at\href{https://github.com/zhang-tao-whu/DVIS}{https://github.com/zhang-tao-whu/DVIS}.

DVIS: Decoupled Video Instance Segmentation Framework