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

Foreground segmentation in video sequences is a classic topic in computervision. Due to the lack of semantic and prior knowledge, it is difficult forexisting methods to deal with sophisticated scenes well. Therefore, in thispaper, we propose an end-to-end two-stage deep convolutional neural network(CNN) framework for foreground segmentation in video sequences. In the firststage, a convolutional encoder-decoder sub-network is employed to reconstructthe background images and encode rich prior knowledge of background scenes. Inthe second stage, the reconstructed background and current frame are input intoa multi-channel fully-convolutional sub-network (MCFCN) for accurate foregroundsegmentation. In the two-stage CNN, the reconstruction loss and segmentationloss are jointly optimized. The background images and foreground objects areoutput simultaneously in an end-to-end way. Moreover, by incorporating theprior semantic knowledge of foreground and background in the pre-trainingprocess, our method could restrain the background noise and keep the integrityof foreground objects at the same time. Experiments on CDNet 2014 show that ourmethod outperforms the state-of-the-art by 4.9%.

Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network