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

Many real-world scenarios, such as human activity recognition (HAR) in IoT,can be formalized as a multi-task multi-view learning problem. Each specifictask consists of multiple shared feature views collected from multiple sources,either homogeneous or heterogeneous. Common among recent approaches is toemploy a typical hard/soft sharing strategy at the initial phase separately foreach view across tasks to uncover common knowledge, underlying the assumptionthat all views are conditionally independent. On the one hand, multiple viewsacross tasks possibly relate to each other under practical situations. On theother hand, supervised methods might be insufficient when labeled data isscarce. To tackle these challenges, we introduce a novel framework ASM2TV forsemi-supervised multi-task multi-view learning. We present a new perspectivenamed gating control policy, a learnable task-view-interacted sharing policythat adaptively selects the most desirable candidate shared block for any viewacross any task, which uncovers more fine-grained task-view-interactedrelatedness and improves inference efficiency. Significantly, our proposedgathering consistency adaption procedure takes full advantage of large amountsof unlabeled fragmented time-series, making it a general framework thataccommodates a wide range of applications. Experiments on two diversereal-world HAR benchmark datasets collected from various subjects and sourcesdemonstrate our framework's superiority over other state-of-the-arts. Thedetailed codes are available at https://github.com/zachstarkk/ASM2TV.

ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework for Human Activity Recognition