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

Different from traditional action recognition based on video segments, onlineaction recognition aims to recognize actions from unsegmented streams of datain a continuous manner. One way for online recognition is based on the evidenceaccumulation over time to make predictions from stream videos. This paperpresents a fast yet effective method to recognize actions from stream of noisyskeleton data, and a novel weighted covariance descriptor is adopted toaccumulate evidence. In particular, a fast incremental updating method for theweighted covariance descriptor is developed for accumulation of temporalinformation and online prediction. The weighted covariance descriptor takes thefollowing principles into consideration: past frames have less contribution forrecognition and recent and informative frames such as key frames contributemore to the recognition. The online recognition is achieved using a simplenearest neighbor search against a set of offline trained action models.Experimental results on MSC-12 Kinect Gesture dataset and our newly constructedonline action recognition dataset have demonstrated the efficacy of theproposed method.

Online Action Recognition based on Incremental Learning of Weighted Covariance Descriptors