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

Recently, facial landmark detection algorithms have achieved remarkableperformance on static images. However, these algorithms are neither accuratenor stable in motion-blurred videos. The missing of structure information makesit difficult for state-of-the-art facial landmark detection algorithms to yieldgood results. In this paper, we propose a framework named FAB that takesadvantage of structure consistency in the temporal dimension for faciallandmark detection in motion-blurred videos. A structure predictor is proposedto predict the missing face structural information temporally, which serves asa geometry prior. This allows our framework to work as a virtuous circle. Onone hand, the geometry prior helps our structure-aware deblurring networkgenerates high quality deblurred images which lead to better landmark detectionresults. On the other hand, better landmark detection results help structurepredictor generate better geometry prior for the next frame. Moreover, it is aflexible video-based framework that can incorporate any static image-basedmethods to provide a performance boost on video datasets. Extensive experimentson Blurred-300VW, the proposed Real-world Motion Blur (RWMB) datasets and 300VWdemonstrate the superior performance to the state-of-the-art methods. Datasetsand models will be publicly available athttps://keqiangsun.github.io/projects/FAB/FAB.html.

FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred Videos