Saved in:
Bibliographic Details
Main Authors: Liu, Zhendong, Zhang, Le, Li, Bing, Zhou, Yingjie, Chen, Zhenghua, Zhu, Ce
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.16233
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915122224562176
author Liu, Zhendong
Zhang, Le
Li, Bing
Zhou, Yingjie
Chen, Zhenghua
Zhu, Ce
author_facet Liu, Zhendong
Zhang, Le
Li, Bing
Zhou, Yingjie
Chen, Zhenghua
Zhu, Ce
contents We address the challenge of WiFi-based temporal activity detection and propose an efficient Dual Pyramid Network that integrates Temporal Signal Semantic Encoders and Local Sensitive Response Encoders. The Temporal Signal Semantic Encoder splits feature learning into high and low-frequency components, using a novel Signed Mask-Attention mechanism to emphasize important areas and downplay unimportant ones, with the features fused using ContraNorm. The Local Sensitive Response Encoder captures fluctuations without learning. These feature pyramids are then combined using a new cross-attention fusion mechanism. We also introduce a dataset with over 2,114 activity segments across 553 WiFi CSI samples, each lasting around 85 seconds. Extensive experiments show our method outperforms challenging baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16233
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network
Liu, Zhendong
Zhang, Le
Li, Bing
Zhou, Yingjie
Chen, Zhenghua
Zhu, Ce
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Networking and Internet Architecture
We address the challenge of WiFi-based temporal activity detection and propose an efficient Dual Pyramid Network that integrates Temporal Signal Semantic Encoders and Local Sensitive Response Encoders. The Temporal Signal Semantic Encoder splits feature learning into high and low-frequency components, using a novel Signed Mask-Attention mechanism to emphasize important areas and downplay unimportant ones, with the features fused using ContraNorm. The Local Sensitive Response Encoder captures fluctuations without learning. These feature pyramids are then combined using a new cross-attention fusion mechanism. We also introduce a dataset with over 2,114 activity segments across 553 WiFi CSI samples, each lasting around 85 seconds. Extensive experiments show our method outperforms challenging baselines.
title WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Networking and Internet Architecture
url https://arxiv.org/abs/2412.16233