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

When we say a person is texting, can you tell the person is walking orsitting? Emphatically, no. In order to solve this incomplete representationproblem, this paper presents a sub-action descriptor for detailed actiondetection. The sub-action descriptor consists of three levels: the posture, thelocomotion, and the gesture level. The three levels give three sub-actioncategories for one action to address the representation problem. The proposedaction detection model simultaneously localizes and recognizes the actions ofmultiple individuals in video surveillance using appearance-based temporalfeatures with multi-CNN. The proposed approach achieved a mean averageprecision (mAP) of 76.6% at the frame-based and 83.5% at the video-basedmeasurement on the new large-scale ICVL video surveillance dataset that theauthors introduce and make available to the community with this paper.Extensive experiments on the benchmark KTH dataset demonstrate that theproposed approach achieved better performance, which in turn boosts the actionrecognition performance over the state-of-the-art. The action detection modelcan run at around 25 fps on the ICVL and more than 80 fps on the KTH dataset,which is suitable for real-time surveillance applications.

Real-Time Action Detection in Video Surveillance using Sub-Action Descriptor with Multi-CNN