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

A fundamental challenge in machine learning today is to build a model thatcan learn from few examples. Here, we describe a reservoir based spiking neuralmodel for learning to recognize actions with a limited number of labeledvideos. First, we propose a novel encoding, inspired by how microsaccadesinfluence visual perception, to extract spike information from raw video datawhile preserving the temporal correlation across different frames. Using thisencoding, we show that the reservoir generalizes its rich dynamical activitytoward signature action/movements enabling it to learn from few trainingexamples. We evaluate our approach on the UCF-101 dataset. Our experimentsdemonstrate that our proposed reservoir achieves 81.3%/87% Top-1/Top-5accuracy, respectively, on the 101-class data while requiring just 8 videoexamples per class for training. Our results establish a new benchmark foraction recognition from limited video examples for spiking neural models whileyielding competetive accuracy with respect to state-of-the-art non-spikingneural models.

Learning to Recognize Actions from Limited Training Examples Using a Recurrent Spiking Neural Model