AMAR: Lightweight Attention-Based Multi-User Activity Recognition from Wi-Fi CSI

• URL: http://arxiv.org/abs/2605.20649v1
• Date: Wed, 20 May 2026 03:09:45 GMT
• Title: AMAR: Lightweight Attention-Based Multi-User Activity Recognition from Wi-Fi CSI
• Abstract summary: Wi-Fi-based human activity recognition (HAR) has emerged as a promising approach for contactless sensing.<n>This paper introduces an attention-based multi-user activity recognition framework that formulates HAR as a set prediction problem.
• Score: 15.684101182919497
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Wi-Fi-based human activity recognition (HAR) has emerged as a promising approach for contactless sensing, leveraging channel state information (CSI) collected from wireless transceivers. While existing studies have primarily concentrated on single-user scenarios, real-world deployments often involve multi-user settings where concurrent users' movements induce overlapping CSI patterns that challenge conventional classification methods. To address this limitation, this paper introduces an attention-based multi-user activity recognition (AMAR) framework that formulates HAR as a set prediction problem. The transformer-based architecture in AMAR leverages learnable query embeddings acting as specialized activity detectors, enabling the simultaneous identification of multiple activities from composite CSI representations. Moreover, to address deployment constraints, AMAR is designed in an edge-cloud split architecture form where lightweight convolutional networks on edge devices perform initial feature extraction, followed by residual vector quantization that achieves substantial bandwidth reduction while preserving activity-discriminative information. The cloud component performs final activity prediction through attention-based set matching, enabling the system to handle varying occupancy levels. Across classroom, meeting-room, and empty-room environments, on average AMAR nearly doubles the rate of perfectly predicting all concurrent activities compared to the best baseline. Moreover, it achieves an $F_1$-score of 53.4% compared to 45.6% for the best benchmark, and reduces occupancy estimation error by 74%, while minimizing bandwidth substantially.

Related papers

• COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm [59.26203051651017]
  C-TAO is the first continuously annotated training set for Open-Vocabulary Multi-Object Tracking (OVMOT)<n>For the framework bottleneck, we propose COVTrack++, a synergistic framework that achieves a bidirectional reciprocal mechanism between detection and association through three modules.<n>Experiments on TAO demonstrate state-of-the-art performance, with novel TETA reaching 35.4% and 30.5% on validation and test sets, improving novel AssocA by 4.8% and novel LocA by 5.8% over previous methods.
  arXiv  Detail & Related papers  (2026-03-25T07:20:27Z)
• Hybrid Deep Learning Framework for CSI-Based Activity Recognition in Bandwidth-Constrained Wi-Fi Sensing [1.0554048699217669]
  This paper presents a novel hybrid deep learning framework designed to enhance the robustness of CSI-based Human Activity Recognition (HAR)<n>The framework's efficacy was systematically validated using a public dataset across 20, 40, and 80 MHz bandwidth configurations.
  arXiv  Detail & Related papers  (2026-01-27T12:42:07Z)
• Cross-Domain Multi-Person Human Activity Recognition via Near-Field Wi-Fi Sensing [20.1340684071988]
  We propose WiAnchor, a novel training framework for efficient cross-domain adaptation in the presence of incomplete activity categories.<n>We construct a comprehensive dataset to thoroughly evaluate WiAnchor, achieving over 90% cross-domain accuracy with absent activity categories.
  arXiv  Detail & Related papers  (2025-09-27T03:22:15Z)
• CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing [13.709208651007167]
  WiFi sensing has emerged as a compelling contactless modality for human activity monitoring by capturing fine-grained variations in Channel State Information (CSI)<n>Existing WiFi sensing systems struggle to generalize in real-world settings due to datasets collected in controlled environments with homogeneous hardware and fragmented, session-based recordings that fail to reflect daily activity.<n>We present CSI-Bench, a large-scale, in-the-wild benchmark dataset collected using commercial WiFi edge devices across 26 diverse indoor environments with 35 real users.
  arXiv  Detail & Related papers  (2025-05-28T01:29:29Z)
• Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference [54.53508601749513]
  We propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework.<n>To enhance compression efficiency, multiple entropy models are adaptively selected based on the characteristics of the visual features.<n>Results show that TOFC achieves up to 52% reduction in data transmission overhead and 63% reduction in system latency.
  arXiv  Detail & Related papers  (2025-03-17T08:37:22Z)
• Cross-Domain Continual Learning for Edge Intelligence in Wireless ISAC Networks [24.55741355643116]
  Edge intelligence (EI) is expected to be developed at edge devices (EDs) for sensing user activities based on channel state information (CSI)<n>Due to the CSI being highly specific to users' characteristics, the CSI-activity relationship is notoriously domain dependent.<n>We propose the EdgeCL framework, enabling the EI to continually learn-then-discard each incoming dataset.
  arXiv  Detail & Related papers  (2025-02-18T10:50:47Z)
• PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
  We propose a. Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns. We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
  arXiv  Detail & Related papers  (2024-06-04T13:51:08Z)
• HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional Mamba [7.412537185607976]
  Wearable sensor-based human activity recognition (HAR) is a critical research domain in activity perception. This study introduces HARMamba, an innovative light-weight and versatile HAR architecture that combines selective bidirectional State Spaces Model and hardware-aware design. HarMamba outperforms contemporary state-of-the-art frameworks, delivering comparable or better accuracy with significantly reducing computational and memory demands.
  arXiv  Detail & Related papers  (2024-03-29T13:57:46Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Joint User and Data Detection in Grant-Free NOMA with Attention-based BiLSTM Network [14.569960447904327]
  We propose an attention-based bidirectional long short-term memory (BiLSTM) network to solve the multi-user detection problem. The proposed framework does not require prior knowledge of device sparsity levels and channels for performing MUD. The results show that the proposed network achieves better performance compared to existing benchmark schemes.
  arXiv  Detail & Related papers  (2022-09-14T03:18:23Z)
• Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AI [108.08079323459822]
  This paper studies a new multi-intelligent edge artificial-latency (AI) system, which jointly exploits the AI model split inference and integrated sensing and communication (ISAC) We measure the inference accuracy by adopting an approximate but tractable metric, namely discriminant gain.
  arXiv  Detail & Related papers  (2022-07-03T06:57:07Z)
• Identity-Aware Attribute Recognition via Real-Time Distributed Inference in Mobile Edge Clouds [53.07042574352251]
  We design novel models for pedestrian attribute recognition with re-ID in an MEC-enabled camera monitoring system. We propose a novel inference framework with a set of distributed modules, by jointly considering the attribute recognition and person re-ID. We then devise a learning-based algorithm for the distributions of the modules of the proposed distributed inference framework.
  arXiv  Detail & Related papers  (2020-08-12T12:03:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.