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

Using deep learning, this paper addresses the problem of joint objectboundary detection and boundary motion estimation in videos, which we namedboundary flow estimation. Boundary flow is an important mid-level visual cue asboundaries characterize objects spatial extents, and the flow indicates objectsmotions and interactions. Yet, most prior work on motion estimation has focusedon dense object motion or feature points that may not necessarily reside onboundaries. For boundary flow estimation, we specify a new fully convolutionalSiamese network (FCSN) that jointly estimates object-level boundaries in twoconsecutive frames. Boundary correspondences in the two frames are predicted bythe same FCSN with a new, unconventional deconvolution approach. Finally, theboundary flow estimate is improved with an edgelet-based filtering. Evaluationis conducted on three tasks: boundary detection in videos, boundary flowestimation, and optical flow estimation. On boundary detection, we achieve thestate-of-the-art performance on the benchmark VSB100 dataset. On boundary flowestimation, we present the first results on the Sintel training dataset. Foroptical flow estimation, we run the recent approach CPMFlow but on theaugmented input with our boundary-flow matches, and achieve significantperformance improvement on the Sintel benchmark.

Boundary Flow: A Siamese Network that Predicts Boundary Motion without Training on Motion