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

Accurate indoor crowd counting (ICC) is a key enabler to many smarthome/office applications. In this paper, we propose a Domain-Agnostic andSample-Efficient wireless indoor crowd Counting (DASECount) framework thatsuffices to attain robust cross-domain detection accuracy given very limiteddata samples in new domains. DASECount leverages the wisdom of few-shotlearning (FSL) paradigm consisting of two major stages: source domain metatraining and target domain meta testing. Specifically, in the meta-trainingstage, we design and train two separate convolutional neural network (CNN)modules on the source domain dataset to fully capture the implicit amplitudeand phase features of CSI measurements related to human activities. Asubsequent knowledge distillation procedure is designed to iteratively updatethe CNN parameters for better generalization performance. In the meta-testingstage, we use the partial CNN modules to extract low-dimension features out ofthe high-dimension input target domain CSI data. With the obtainedlow-dimension CSI features, we can even use very few shots of target domaindata samples (e.g., 5-shot samples) to train a lightweight logistic regression(LR) classifier, and attain very high cross-domain ICC accuracy. Experimentresults show that the proposed DASECount method achieves over 92.68\%, and onaverage 96.37\% detection accuracy in a 0-8 people counting task under variousdomain setups, which significantly outperforms the other representativebenchmark methods considered.

DASECount: Domain-Agnostic Sample-Efficient Wireless Indoor Crowd Counting via Few-shot Learning