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

This paper addresses fast semantic segmentation on video.Video segmentationoften calls for real-time, or even fasterthan real-time, processing. One commonrecipe for conserving computation arising from feature extraction is topropagate features of few selected keyframes. However, recent advances in fastimage segmentation make these solutions less attractive. To leverage fast imagesegmentation for furthering video segmentation, we propose a simple yetefficient propagation framework. Specifically, we perform lightweight flowestimation in 1/8-downscaled image space for temporal warping in segmentationoutpace space. Moreover, we introduce a guided spatially-varying convolutionfor fusing segmentations derived from the previous and current frames, tomitigate propagation error and enable lightweight feature extraction onnon-keyframes. Experimental results on Cityscapes and CamVid show that ourscheme achieves the state-of-the-art accuracy-throughput trade-off on videosegmentation.

GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video