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

In this paper, Gated-ViGAT, an efficient approach for video eventrecognition, utilizing bottom-up (object) information, a new frame samplingpolicy and a gating mechanism is proposed. Specifically, the frame samplingpolicy uses weighted in-degrees (WiDs), derived from the adjacency matrices ofgraph attention networks (GATs), and a dissimilarity measure to select the mostsalient and at the same time diverse frames representing the event in thevideo. Additionally, the proposed gating mechanism fetches the selected framessequentially, and commits early-exiting when an adequately confident decisionis achieved. In this way, only a few frames are processed by thecomputationally expensive branch of our network that is responsible for thebottom-up information extraction. The experimental evaluation on two large,publicly available video datasets (MiniKinetics, ActivityNet) demonstrates thatGated-ViGAT provides a large computational complexity reduction in comparisonto our previous approach (ViGAT), while maintaining the excellent eventrecognition and explainability performance. Gated-ViGAT source code is madepublicly available at https://github.com/bmezaris/Gated-ViGAT

Gated-ViGAT: Efficient Bottom-Up Event Recognition and Explanation Using a New Frame Selection Policy and Gating Mechanism