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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this letter, we propose a new method, Multi-Clue Gaze (MCGaze), tofacilitate video gaze estimation via capturing spatial-temporal interactioncontext among head, face, and eye in an end-to-end learning way, which has notbeen well concerned yet. The main advantage of MCGaze is that the tasks of cluelocalization of head, face, and eye can be solved jointly for gaze estimationin a one-step way, with joint optimization to seek optimal performance. Duringthis, spatial-temporal context exchange happens among the clues on the head,face, and eye. Accordingly, the final gazes obtained by fusing features fromvarious queries can be aware of global clues from heads and faces, and localclues from eyes simultaneously, which essentially leverages performance.Meanwhile, the one-step running way also ensures high running efficiency.Experiments on the challenging Gaze360 dataset verify the superiority of ourproposition. The source code will be released athttps://github.com/zgchen33/MCGaze.

End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context