arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.08643cs.LGcs.AIcs.MM
收藏

ASM2TV:一种用于人体活动识别的自适应半监督多任务多视图学习框架

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

George Washington University(乔治华盛顿大学);Shandong University(山东大学)

Zekai Chen, Xiao Zhang, Xiuzhen Cheng

摘要:

许多现实世界的场景,例如物联网中的人类活动识别(HAR),可以形式化为多任务多视图学习问题。每个特定的任务都由多个共享的特征视图组成,这些特征视图是从多个同源或异构源收集的。在最近的方法中,共同的是采用典型的硬/软共享策略,在初始阶段分别为每个视图跨任务,以揭示共同的知识,假设所有的视图是有条件的独立。一方面,在实际情况下,跨任务的多个视图可能相互关联。另一方面,当标记数据稀缺时,监督方法可能不够。为了解决这些挑战,我们引入了一个新的框架ASM 2 TV用于半监督多任务多视图学习。我们提出了一个新的视角命名为门控策略,一个可学习的任务视图交互共享策略,自适应地选择最理想的候选共享块的任何视图在任何任务,揭示更细粒度的任务视图交互的相关性,提高推理效率。值得注意的是,我们提出的收集一致性自适应过程充分利用了大量未标记的碎片时间序列,使其成为一个通用的框架,可容纳广泛的应用。两个不同的真实世界的HAR基准数据集从不同的主题和来源收集的实验表明,我们的框架的优越性,比其他国家的最先进的。详细代码可在https://github.com/zachstarkk/ASM2TV上获得。

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑