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

Human Activity Recognition (HAR) systems have been extensively studied by thevision and ubiquitous computing communities due to their practical applicationsin daily life, such as smart homes, surveillance, and health monitoring.  Typically, this process is supervised in nature and the development of suchsystems requires access to large quantities of annotated data.  However, the higher costs and challenges associated with obtaining goodquality annotations have rendered the application of self-supervised methods anattractive option and contrastive learning comprises one such method.  However, a major component of successful contrastive learning is theselection of good positive and negative samples.  Although positive samples are directly obtainable, sampling good negativesamples remain a challenge.  As human activities can be recorded by several modalities like camera and IMUsensors, we propose a hard negative sampling method for multimodal HAR with ahard negative sampling loss for skeleton and IMU data pairs.  We exploit hard negatives that have different labels from the anchor but areprojected nearby in the latent space using an adjustable concentrationparameter.  Through extensive experiments on two benchmark datasets: UTD-MHAD and MMAct,we demonstrate the robustness of our approach forlearning strong featurerepresentation for HAR tasks, and on the limited data setting.  We further show that our model outperforms all other state-of-the-art methodsfor UTD-MHAD dataset, and self-supervised methods for MMAct: Cross session,even when uni-modal data are used during downstream activity recognition.

Multimodal Contrastive Learning with Hard Negative Sampling for Human Activity Recognition