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

Video analysis is a major computer vision task that has received a lot ofattention in recent years. The current state-of-the-art performance for videoanalysis is achieved with Deep Neural Networks (DNNs) that have highcomputational costs and need large amounts of labeled data for training.Spiking Neural Networks (SNNs) have significantly lower computational costs(thousands of times) than regular non-spiking networks when implemented onneuromorphic hardware. They have been used for video analysis with methods like3D Convolutional Spiking Neural Networks (3D CSNNs). However, these networkshave a significantly larger number of parameters compared with spiking 2D CSNN.This, not only increases the computational costs, but also makes these networksmore difficult to implement with neuromorphic hardware. In this work, we useCSNNs trained in an unsupervised manner with the Spike Timing-DependentPlasticity (STDP) rule, and we introduce, for the first time, Spiking SeparatedSpatial and Temporal Convolutions (S3TCs) for the sake of reducing the numberof parameters required for video analysis. This unsupervised learning has theadvantage of not needing large amounts of labeled data for training.Factorizing a single spatio-temporal spiking convolution into a spatial and atemporal spiking convolution decreases the number of parameters of the network.We test our network with the KTH, Weizmann, and IXMAS datasets, and we showthat S3TCs successfully extract spatio-temporal information from videos, whileincreasing the output spiking activity, and outperforming spiking 3Dconvolutions.

S3TC: Spiking Separated Spatial and Temporal Convolutions with Unsupervised STDP-based Learning for Action Recognition