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

Recent studies have shown that video-level representation learning is crucialto the capture and understanding of the long-range temporal structure for videoaction recognition. Most existing 3D convolutional neural network (CNN)-basedmethods for video-level representation learning are clip-based and focus onlyon short-term motion and appearances. These CNN-based methods lack the capacityto incorporate and model the long-range spatiotemporal representation of theunderlying video and ignore the long-range video-level context during training.In this study, we propose a factorized 4D CNN architecture with attention (F4D)that is capable of learning more effective, finer-grained, long-termspatiotemporal video representations. We demonstrate that the proposed F4Darchitecture yields significant performance improvements over the conventional2D, and 3D CNN architectures proposed in the literature. Experiment evaluationon five action recognition benchmark datasets, i.e., Something-Something-v1,SomethingSomething-v2, Kinetics-400, UCF101, and HMDB51 demonstrate theeffectiveness of the proposed F4D network architecture for video-level actionrecognition.

F4D: Factorized 4D Convolutional Neural Network for Efficient Video-level Representation Learning