GOAT: A Generalized Cross-Dataset Activity Recognition Framework with Natural Language Supervision
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · 21.11.2024 · 8 (4) · 1-28
DOI: 10.1145/3699736 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, online erschienen am 21.11.2024. Verfasst von Shenghuan Miao und 1 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 91 Literaturangaben.
Abstract (Originalsprache)
Wearable human activity recognition faces challenges in cross-dataset generalization due to variations in device configurations and activity types across datasets. We present GOAT, a Generalized crOss-dataset Activity recogniTion framework that leverages learning with natural language supervision to address these challenges. GOAT utilizes textual attributes from activity labels and device on-body positions to enable multimodal pre-training, aligning wearable activity representations with corresponding textual representations. This approach enables GOAT to adapt to diverse device configurations and activity label spaces in downstream tasks. Our method incorporates a novel device position encoding technique, a Transformer-based activity encoder, and a cosine similarity loss function to enhance feature extraction and generalization capabilities. Extensive evaluations demonstrate GOAT's effectiveness across various scenarios, including comparisons with state-of-the-art baselines, component analysis, and zero-shot activity recognition. GOAT shows promise for advancing cross-dataset activity recognition, offering a flexible and scalable solution for diverse wearable sensing applications.
Zitieren
APA
Miao, S., & Chen, L. (2024). GOAT: A Generalized Cross-Dataset Activity Recognition Framework with Natural Language Supervision. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 8(4), 1-28. https://doi.org/10.1145/3699736
Vancouver
Miao S, Chen L. GOAT: A Generalized Cross-Dataset Activity Recognition Framework with Natural Language Supervision. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. 2024;8(4):1-28. doi:10.1145/3699736
BibTeX
@article{Miao2024,
author = {Miao, Shenghuan and Chen, Ling},
title = {GOAT: A Generalized Cross-Dataset Activity Recognition Framework with Natural Language Supervision},
journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},
year = {2024},
volume = {8},
number = {4},
pages = {1--28},
doi = {10.1145/3699736}
}
EUVIMED