Can I read Self-relation Attention Networks for Weakly Supervised Few-shot Activity Recognition on EtoBox?

Self-relation Attention Networks for Weakly Supervised Few-shot Activity Recognition by Shizhuo Deng; Zhubao Guo; Da Teng; Boqian Lin; Dongyue Chen; Tong Jia; Hao Wang is a Computer Science article available to read on EtoBox.

What is Self-relation Attention Networks for Weakly Supervised Few-shot Activity Recognition about?

Traditional sensor-based human activity recognition (HAR), which requires a large amount of high-quality data of a new class for training, can hardly classify new-class activities given only a few labeled samples. Using these models to customize and recognize personalized (new class) activity for a better user experience is a great challenge. It is time-consuming work for users to label abundant new-class time series data. Additionally, these activity sequences are weakly-labeled with existing annotation technology. The purpose of this work is to learn a meta-classifier that generalizes well in weakly-labeled new-class activities even given few noisy samples. On this basis, we combine the power of few-shot learning and weakly supervised classification to achieve the above goal. We propose a novel self-relation attention Prototypical Networks for personalized HAR to extract more discriminative target features from the spatiotemporal features of noisy sensor data. Attention-based meta-learning generates each subsequence contribution to the object activity features automatically on the subsequence-level relation mining in one weakly labeled sample. Therefore, the highlighted object ac

Who reads Self-relation Attention Networks for Weakly Supervised Few-shot Activity Recognition?

Author

Shizhuo Deng; Zhubao Guo; Da Teng; Boqian Lin; Dongyue Chen; Tong Jia; Hao Wang

Publisher

Elsevier BV

Published

2023

Language

EN

Field

Computer Science (Physical Sciences)