File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: GraSens: A Gabor Residual Anti-aliasing Sensing Framework for Action Recognition using WiFi

TitleGraSens: A Gabor Residual Anti-aliasing Sensing Framework for Action Recognition using WiFi
Authors
Issue Date2022
Citation
Proceedings - International Conference on Pattern Recognition, 2022, v. 2022-August, p. 288-295 How to Cite?
AbstractWiFi-based human action recognition (HAR) has been regarded as a promising solution in applications such as smart living and remote monitoring due to the pervasive and unobtrusive nature of WiFi signals. However, the efficacy of WiFi signals is prone to be influenced by the change in the ambient environment and varies over different sub-carriers. To remedy this issue, we propose an end-to-end Gabor residual anti-aliasing sensing network (GraSens) to directly recognize the actions using the WiFi signals from the wireless devices in diverse scenarios. In particular, a new Gabor residual block is designed to address the impact of the changing surrounding environment with a focus on learning reliable and robust temporal-frequency representations of WiFi signals. In each block, the Gabor layer is integrated with the anti-aliasing layer in a residual manner to gain the shift-invariant features. Furthermore, fractal temporal and frequency self-attention are proposed in a joint effort to explicitly concentrate on the efficacy of WiFi signals and thus enhance the quality of output features scattered in different subcarriers. Experimental results throughout our wireless-vision action recognition dataset (WVAR) and three public datasets demonstrate that our proposed GraSens scheme outperforms state-of-the-art methods with respect to recognition accuracy.
Persistent Identifierhttp://hdl.handle.net/10722/349829
ISSN
2023 SCImago Journal Rankings: 0.584

 

DC FieldValueLanguage
dc.contributor.authorHao, Yanling-
dc.contributor.authorShi, Zhiyuan-
dc.contributor.authorMu, Xidong-
dc.contributor.authorLiu, Yuanwei-
dc.date.accessioned2024-10-17T07:01:11Z-
dc.date.available2024-10-17T07:01:11Z-
dc.date.issued2022-
dc.identifier.citationProceedings - International Conference on Pattern Recognition, 2022, v. 2022-August, p. 288-295-
dc.identifier.issn1051-4651-
dc.identifier.urihttp://hdl.handle.net/10722/349829-
dc.description.abstractWiFi-based human action recognition (HAR) has been regarded as a promising solution in applications such as smart living and remote monitoring due to the pervasive and unobtrusive nature of WiFi signals. However, the efficacy of WiFi signals is prone to be influenced by the change in the ambient environment and varies over different sub-carriers. To remedy this issue, we propose an end-to-end Gabor residual anti-aliasing sensing network (GraSens) to directly recognize the actions using the WiFi signals from the wireless devices in diverse scenarios. In particular, a new Gabor residual block is designed to address the impact of the changing surrounding environment with a focus on learning reliable and robust temporal-frequency representations of WiFi signals. In each block, the Gabor layer is integrated with the anti-aliasing layer in a residual manner to gain the shift-invariant features. Furthermore, fractal temporal and frequency self-attention are proposed in a joint effort to explicitly concentrate on the efficacy of WiFi signals and thus enhance the quality of output features scattered in different subcarriers. Experimental results throughout our wireless-vision action recognition dataset (WVAR) and three public datasets demonstrate that our proposed GraSens scheme outperforms state-of-the-art methods with respect to recognition accuracy.-
dc.languageeng-
dc.relation.ispartofProceedings - International Conference on Pattern Recognition-
dc.titleGraSens: A Gabor Residual Anti-aliasing Sensing Framework for Action Recognition using WiFi-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICPR56361.2022.9956179-
dc.identifier.scopuseid_2-s2.0-85143629273-
dc.identifier.volume2022-August-
dc.identifier.spage288-
dc.identifier.epage295-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats