{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T02:59:53Z","timestamp":1780973993748,"version":"3.54.1"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132094","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T10:14:44Z","timestamp":1773828884000},"page":"132094","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Sensor-to-Sensor procedural co-learning for sensor-limited human action recognition"],"prefix":"10.1016","volume":"319","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0764-6579","authenticated-orcid":false,"given":"Yulai","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3903-4948","authenticated-orcid":false,"given":"Yijia","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4822-8338","authenticated-orcid":false,"given":"Qing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2251-9220","authenticated-orcid":false,"given":"Fang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.eswa.2026.132094_bib0001","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal Machine Learning: A Survey and Taxonomy","volume":"41","author":"Baltrusaitis","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"12","key":"10.1016\/j.eswa.2026.132094_bib0002","doi-asserted-by":"crossref","first-page":"4596","DOI":"10.3390\/s22124596","article-title":"The State-of-the-Art Sensing Techniques in Human Activity Recognition: A Survey","volume":"22","author":"Bian","year":"2022","journal-title":"Sensors"},{"issue":"3","key":"10.1016\/j.eswa.2026.132094_bib0003","doi-asserted-by":"crossref","DOI":"10.1145\/2499621","article-title":"A tutorial on human activity recognition using body-worn inertial sensors","volume":"46","author":"Bulling","year":"2014","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.eswa.2026.132094_bib0004","unstructured":"Chen, B., Wongso, W., Li, Z., Khaokaew, Y., Xue, H., & Salim, F. (2025). COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition. 10.48550\/arXiv.2503.07259."},{"key":"10.1016\/j.eswa.2026.132094_bib0005","series-title":"2015 IEEE International Conference on Image Processing (ICIP)","first-page":"168","article-title":"UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor","author":"Chen","year":"2015"},{"key":"10.1016\/j.eswa.2026.132094_bib0006","series-title":"Proceedings of the 37th International Conference on Machine Learning","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.eswa.2026.132094_bib0007","series-title":"Proceedings of the International Conference on Learning Representations (ICLR 2025)","first-page":"1","article-title":"X-Fi: A Modality-Invariant Foundation Model for Multimodal Human Sensing","author":"Chen","year":"2025"},{"key":"10.1016\/j.eswa.2026.132094_bib0008","unstructured":"van den, O. A., Li, Y., & Vinyals, O. (2018). Representation Learning with Contrastive Predictive Coding. 10.48550\/arXiv.1807.03748."},{"issue":"12","key":"10.1016\/j.eswa.2026.132094_bib0009","first-page":"1234","article-title":"Hypergraph-based Multi-View Action Recognition using Event Cameras","volume":"46","author":"Gao","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132094_bib0010","series-title":"Computer vision - ECCV 2018","first-page":"106","article-title":"Modality Distillation with Multiple Stream Networks for Action Recognition","volume":"vol. 11212","author":"Garcia","year":"2018"},{"key":"10.1016\/j.eswa.2026.132094_bib0011","series-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","first-page":"1533","article-title":"Deep, convolutional, and recurrent models for human activity recognition using wearables","author":"Hammerla","year":"2016"},{"key":"10.1016\/j.eswa.2026.132094_bib0012","series-title":"Pattern Recognition","first-page":"425","article-title":"LightHART: Lightweight Human Activity Recognition Transformer","author":"Haque","year":"2025"},{"key":"10.1016\/j.eswa.2026.132094_bib0013","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Momentum Contrast for Unsupervised Visual Representation Learning","author":"He","year":"2020"},{"key":"10.1016\/j.eswa.2026.132094_bib0014","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the Knowledge in a Neural Network. Preprint. arXiv: 1503.02531. NIPS 2014 Deep Learning Workshophttp:\/\/arxiv.org\/abs\/1503.02531."},{"key":"10.1016\/j.eswa.2026.132094_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2025.104645","article-title":"Multi-modal deep facial expression recognition framework combining knowledge distillation and retrieval-augmented generation","volume":"114","author":"Jiang","year":"2026","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"10.1016\/j.eswa.2026.132094_bib0016","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"8657","article-title":"MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding","author":"Kong","year":"2019"},{"issue":"1","key":"10.1016\/j.eswa.2026.132094_bib0017","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On Information and Sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Annals of Mathematical Statistics"},{"issue":"3","key":"10.1016\/j.eswa.2026.132094_bib0018","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1109\/SURV.2012.110112.00192","article-title":"A Survey on Human Activity Recognition using Wearable Sensors","volume":"15","author":"Lara","year":"2013","journal-title":"IEEE Communications Surveys & Tutorials"},{"key":"10.1016\/j.eswa.2026.132094_bib0019","article-title":"CrossFuse: A Novel Cross Attention Mechanism based Infrared and Visible Image Fusion Approach","volume":"109","author":"Li","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132094_bib0020","unstructured":"Liu, H., Li, S., Yu, Y., Jiang, Y., Xiao, H., Long, J., Tang, H., & Li, C. (2025). CMD-HAR: Cross-Modal Disentanglement for Wearable Human Activity Recognition. 10.48550\/arXiv.2503.21843."},{"key":"10.1016\/j.eswa.2026.132094_bib0021","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, K., Li, G., & Lin, L. (2021). Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition. IEEE Transactions on Image Processing, 30, 5573\u20135588. arXiv: 2009.00210 [cs]. 10.1109\/TIP.2021.3086590.","DOI":"10.1109\/TIP.2021.3086590"},{"key":"10.1016\/j.eswa.2026.132094_bib0022","series-title":"Computer vision \u2013 ECCV 2018","first-page":"174","article-title":"Graph Distillation for Action Detection with Privileged Modalities","volume":"vol. 11218","author":"Luo","year":"2018"},{"key":"10.1016\/j.eswa.2026.132094_bib0023","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"119","article-title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","author":"Munro","year":"2020"},{"key":"10.1016\/j.eswa.2026.132094_bib0024","series-title":"Advances in Neural Information Processing Systems","first-page":"14200","article-title":"Attention Bottlenecks for Multimodal Fusion","volume":"vol. 34","author":"Nagrani","year":"2021"},{"key":"10.1016\/j.eswa.2026.132094_bib0025","doi-asserted-by":"crossref","unstructured":"Nguyen, T. T., Kawanishi, Y., John, V., Komamizu, T., & Ide, I. (2025). MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion. In Proceedings of the 19th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2025)(pp. 1\u201310). IEEE. 10.48550\/arXiv.2504.02287.","DOI":"10.1109\/FG61629.2025.11099071"},{"key":"10.1016\/j.eswa.2026.132094_bib0026","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"4448","article-title":"Cross-modal knowledge distillation for Vision-to-Sensor action recognition","author":"Ni","year":"2022"},{"key":"10.1016\/j.eswa.2026.132094_bib0027","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3962","article-title":"Relational Knowledge Distillation","author":"Park","year":"2019"},{"issue":"10","key":"10.1016\/j.eswa.2026.132094_bib0028","doi-asserted-by":"crossref","first-page":"5734","DOI":"10.1109\/TCSVT.2023.3255832","article-title":"MAWKDN: A Multimodal Fusion Wavelet Knowledge Distillation Approach Based on Cross-View Attention for Action Recognition","volume":"33","author":"Quan","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.132094_bib0029","doi-asserted-by":"crossref","DOI":"10.3389\/fcomp.2025.1569205","article-title":"Improving IMU based human activity recognition using simulated multimodal representations and a MoE classifier","volume":"7","author":"Ray","year":"2025","journal-title":"Frontiers in Computer Science"},{"key":"10.1016\/j.eswa.2026.132094_bib0030","series-title":"Proceedings of the 2015 ACM on International Conference on Multimodal Interaction","first-page":"259","article-title":"Multimodal Human Activity Recognition for Industrial Manufacturing Processes in Robotic Workcells","author":"Roitberg","year":"2015"},{"key":"10.1016\/j.eswa.2026.132094_bib0031","series-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings","article-title":"FitNets: Hints for Thin Deep Nets","author":"Romero","year":"2015"},{"key":"10.1016\/j.eswa.2026.132094_bib0032","series-title":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"614","article-title":"D3D: Distilled 3D Networks for Video Action Recognition","author":"Stroud","year":"2020"},{"issue":"4","key":"10.1016\/j.eswa.2026.132094_bib0033","doi-asserted-by":"crossref","DOI":"10.1145\/3432701","article-title":"MM-Fit: Multimodal Deep Learning for Automatic Exercise Logging across Sensing Devices","volume":"4","author":"Str\u00f6mb\u00e4ck","year":"2020","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"10.1016\/j.eswa.2026.132094_bib0034","series-title":"2019 IEEE International Conference on Image Processing (ICIP)","first-page":"6","article-title":"Cross-modal knowledge distillation for action recognition","author":"Thoker","year":"2019"},{"issue":"6","key":"10.1016\/j.eswa.2026.132094_bib0035","doi-asserted-by":"crossref","first-page":"3101","DOI":"10.1109\/JSEN.2019.2956901","article-title":"Human Action Recognition Using Deep Learning Methods on Limited Sensory Data","volume":"20","author":"Tufek","year":"2020","journal-title":"IEEE Sensors Journal"},{"key":"10.1016\/j.eswa.2026.132094_bib0036","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13286","article-title":"MMTM: Multimodal Transfer Module for CNN Fusion","author":"Vaezi Joze","year":"2020"},{"key":"10.1016\/j.eswa.2026.132094_bib0037","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","article-title":"Deep learning for sensor-based activity recognition: A survey","volume":"119","author":"Wang","year":"2019","journal-title":"Pattern Recognition Letters"},{"issue":"1","key":"10.1016\/j.eswa.2026.132094_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.birob.2023.100089","article-title":"Wearable sensors for activity monitoring and motion control: A review","volume":"3","author":"Wang","year":"2023","journal-title":"Biomimetic Intelligence and Robotics"},{"key":"10.1016\/j.eswa.2026.132094_bib0039","series-title":"Proceedings of the 24th International Conference on Artificial Intelligence","first-page":"3939","article-title":"Imaging time-series to improve classification and imputation","author":"Wang","year":"2015"},{"issue":"11","key":"10.1016\/j.eswa.2026.132094_bib0040","doi-asserted-by":"crossref","first-page":"18578","DOI":"10.1109\/JSEN.2024.3388893","article-title":"Centaur: Robust Multimodal Fusion for Human Activity Recognition","volume":"24","author":"Xaviar","year":"2024","journal-title":"IEEE Sensors Journal"},{"key":"10.1016\/j.eswa.2026.132094_bib0041","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2025)","first-page":"12345","article-title":"Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning","author":"Xiong","year":"2025"},{"key":"10.1016\/j.eswa.2026.132094_bib0042","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7130","article-title":"A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning","author":"Yim","year":"2017"},{"issue":"1","key":"10.1016\/j.eswa.2026.132094_bib0043","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1038\/s41598-025-34401-9","article-title":"ASSAFormer: A sensor data-based approach to human activity recognition","volume":"16","author":"Zeng","year":"2026","journal-title":"Scientific Reports"},{"issue":"12","key":"10.1016\/j.eswa.2026.132094_bib0044","doi-asserted-by":"crossref","first-page":"14144","DOI":"10.1109\/TPAMI.2023.3312302","article-title":"Attribute-Guided Collaborative Learning for Partial Person Re-Identification","volume":"45","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"10.1016\/j.eswa.2026.132094_bib0045","article-title":"Depth Guided Cross-modal Residual Adaptive Network for RGB-D Salient Object Detection","volume":"1873","author":"Zhao","year":"2021","journal-title":"Journal of Physics: Conference Series"},{"key":"10.1016\/j.eswa.2026.132094_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2025.104625","article-title":"Real-time facial expression recognition via quaternion Gabor convolutional neural network","volume":"113","author":"Zhou","year":"2025","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"10.1016\/j.eswa.2026.132094_bib0047","series-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Quaternion Orthogonal Transformer for Facial Expression Recognition in the Wild","author":"Zhou","year":"2023"},{"key":"10.1016\/j.eswa.2026.132094_bib0048","doi-asserted-by":"crossref","first-page":"3895","DOI":"10.1109\/TMM.2025.3535361","article-title":"Delving Into Quaternion Wavelet Transformer for Facial Expression Recognition in the Wild","volume":"27","author":"Zhou","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132094_bib0049","article-title":"Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook","volume":"110","author":"Zou","year":"2024","journal-title":"Information Fusion"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426010079?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426010079?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T02:38:20Z","timestamp":1780972700000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426010079"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":49,"alternative-id":["S0957417426010079"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132094","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Sensor-to-Sensor procedural co-learning for sensor-limited human action recognition","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132094","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132094"}}