dorsal/arxiv
View SchemaMobiDiary: Autoregressive Action Captioning with Wearable Devices and Wireless Signals
| Authors | Fei Deng, Yinghui He, Chuntong Chu, Ge Wang, Han Ding, Jinsong Han, Fei Wang |
|---|---|
| Categories | |
| ArXiv ID | 2601.08204vv1 |
| URL | https://arxiv.org/abs/2601.08204 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Human Activity Recognition (HAR) in smart homes is critical for health monitoring and assistive living. While vision-based systems are common, they face privacy concerns and environmental limitations (e.g., occlusion). In this work, we present MobiDiary, a framework that generates natural language descriptions of daily activities directly from heterogeneous physical signals (specifically IMU and Wi-Fi). Unlike conventional approaches that restrict outputs to pre-defined labels, MobiDiary produces expressive, human-readable summaries. To bridge the semantic gap between continuous, noisy physical signals and discrete linguistic descriptions, we propose a unified sensor encoder. Instead of relying on modality-specific engineering, we exploit the shared inductive biases of motion-induced signals--where both inertial and wireless data reflect underlying kinematic dynamics. Specifically, our encoder utilizes a patch-based mechanism to capture local temporal correlations and integrates heterogeneous placement embedding to unify spatial contexts across different sensors. These unified signal tokens are then fed into a Transformer-based decoder, which employs an autoregressive mechanism to generate coherent action descriptions word-by-word. We comprehensively evaluate our approach on multiple public benchmarks (XRF V2, UWash, and WiFiTAD). Experimental results demonstrate that MobiDiary effectively generalizes across modalities, achieving state-of-the-art performance on captioning metrics (e.g., BLEU@4, CIDEr, RMC) and outperforming specialized baselines in continuous action understanding.
{
"annotation_id": "f9d4c819-9b90-4603-a261-9ee3a8d0fde7",
"date_created": "2026-02-17T05:53:16.194000Z",
"date_modified": "2026-02-17T05:53:16.194000Z",
"file_hash": "138853db80c94a2182be736054b4e43f4855ec3200df5acb430c70b781ca5d8a",
"private": false,
"record": {
"abstract": "Human Activity Recognition (HAR) in smart homes is critical for health monitoring and assistive living. While vision-based systems are common, they face privacy concerns and environmental limitations (e.g., occlusion). In this work, we present MobiDiary, a framework that generates natural language descriptions of daily activities directly from heterogeneous physical signals (specifically IMU and Wi-Fi). Unlike conventional approaches that restrict outputs to pre-defined labels, MobiDiary produces expressive, human-readable summaries. To bridge the semantic gap between continuous, noisy physical signals and discrete linguistic descriptions, we propose a unified sensor encoder. Instead of relying on modality-specific engineering, we exploit the shared inductive biases of motion-induced signals--where both inertial and wireless data reflect underlying kinematic dynamics. Specifically, our encoder utilizes a patch-based mechanism to capture local temporal correlations and integrates heterogeneous placement embedding to unify spatial contexts across different sensors. These unified signal tokens are then fed into a Transformer-based decoder, which employs an autoregressive mechanism to generate coherent action descriptions word-by-word. We comprehensively evaluate our approach on multiple public benchmarks (XRF V2, UWash, and WiFiTAD). Experimental results demonstrate that MobiDiary effectively generalizes across modalities, achieving state-of-the-art performance on captioning metrics (e.g., BLEU@4, CIDEr, RMC) and outperforming specialized baselines in continuous action understanding.",
"arxiv_id": "2601.08204",
"authors": [
"Fei Deng",
"Yinghui He",
"Chuntong Chu",
"Ge Wang",
"Han Ding",
"Jinsong Han",
"Fei Wang"
],
"categories": [
"cs.CV"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "MobiDiary: Autoregressive Action Captioning with Wearable Devices and Wireless Signals",
"url": "https://arxiv.org/abs/2601.08204",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "2332de9a-1fde-4eaf-9b17-af8fd1eef7e5",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}