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

We propose a novel scheme for human action recognition in videos, using a3-dimensional Convolutional Neural Network (3D CNN) based classifier.Traditionally in deep learning based human activity recognition approaches,either a few random frames or every $k^{th}$ frame of the video is consideredfor training the 3D CNN, where $k$ is a small positive integer, like 4, 5, or6. This kind of sampling reduces the volume of the input data, which speeds-uptraining of the network and also avoids over-fitting to some extent, thusenhancing the performance of the 3D CNN model. In the proposed video samplingtechnique, consecutive $k$ frames of a video are aggregated into a single frameby computing a Gaussian-weighted summation of the $k$ frames. The resultingframe (aggregated frame) preserves the information in a better way than theconventional approaches and experimentally shown to perform better. In thispaper, a 3D CNN architecture is proposed to extract the spatio-temporalfeatures and follows Long Short-Term Memory (LSTM) to recognize human actions.The proposed 3D CNN architecture is capable of handling the videos where thecamera is placed at a distance from the performer. Experiments are performedwith KTH and WEIZMANN human actions datasets, whereby it is shown to producecomparable results with the state-of-the-art techniques.

An Information-rich Sampling Technique over Spatio-Temporal CNN for Classification of Human Actions in Videos