活动识别
计算机科学
人工智能
匹配(统计)
人工神经网络
模式识别(心理学)
构造(python库)
适应(眼睛)
相似性(几何)
特征(语言学)
机器学习
数据挖掘
特征提取
机制(生物学)
特征匹配
干扰(通信)
对象(语法)
卷积神经网络
边距(机器学习)
兴旺的
合成数据
视觉对象识别的认知神经科学
作者
Xin Li,Jingzhi Hu,Yinghui He,Hongbo Wang,Jin Gan,Jun Luo
标识
DOI:10.1109/tpami.2026.3729614
摘要
Wi-Fi-based human activity recognition (HAR) provides substantial convenience and has emerged as a thriving research field, yet the coarse spatial resolution inherent to Wi-Fi significantly hinders its ability to distinguish multiple subjects. By exploiting the near-field domination effect, establishing a dedicated sensing link for each subject through their personal Wi-Fi device offers a promising solution for multi-person HAR under native traffic. However, due to the subject-specific characteristics and irregular patterns of near-field signals, HAR neural network models require fine-tuning (FT) for cross-domain adaptation, which becomes particularly challenging with certain categories unavailable. In this paper, we propose WiAnchor, a novel training framework for efficient cross-domain adaptation in the presence of incomplete activity categories. This framework processes Wi-Fi signals embedded with irregular time information in three steps: during pre-training, we enlarge inter-class feature margins to enhance the separability of activities; in the FT stage, we innovate an anchor matching mechanism for cross-domain adaptation, filtering subject-specific interference informed by incomplete activity categories, rather than attempting to extract complete features from them; finally, the recognition of input samples is further improved based on their feature-level similarity with anchors. We construct a comprehensive dataset to thoroughly evaluate WiAnchor, achieving over 90% cross-domain accuracy with absent activity categories under multi-person scenarios.
科研通智能强力驱动
Strongly Powered by AbleSci AI