{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T11:11:56Z","timestamp":1788952316897,"version":"build-2803163510"},"reference-count":39,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972038"],"award-info":[{"award-number":["61972038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["61972038"],"award-info":[{"award-number":["61972038"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Sichuan Provincial Project for Province-University Strategic Cooperation","award":["2026YFHZ0196"],"award-info":[{"award-number":["2026YFHZ0196"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>As an emerging sensing modality, 4D millimeter-wave radar provides a privacy-preserving and lighting-robust solution for indoor scene perception and human action recognition (HAR). However, existing radar-based HAR methods mainly focus on short-term motion dynamics while overlooking the influence of indoor scene context. Furthermore, reconstructing indoor layouts from sparse and irregular radar point clouds remains challenging. To address these issues, this paper proposes an environmental context-aware radar action recognition framework (ECRAR) that jointly models human motion and indoor scene context from 4D millimeter-wave radar point clouds. Specifically, a trajectory-to-floorplan inversion branch reconstructs indoor layouts from long-term trajectory point clouds by exploiting the relationship between human movement distributions and spatial accessibility. A motion feature extraction branch captures discriminative short-term motion representations through multi-scale spatial modeling, while an environmental context fusion module adaptively integrates scene and motion features using cross-attention. We also construct InActivity-Scene, a new dataset with fine-grained scene annotations and nine categories of daily and hazardous human actions collected in multiple indoor environments. Experimental results demonstrate that ECRAR consistently outperforms existing methods, achieving 92.2% recognition accuracy with significant improvements on environment-dependent actions, while ablation studies further verify the effectiveness of each proposed component.<\/jats:p>","DOI":"10.3390\/s26185717","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:19:16Z","timestamp":1788949156000},"page":"5717","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Environmental Context-Aware Human Action Recognition from 4D Millimeter-Wave Radar Point Clouds"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6699-3891","authenticated-orcid":false,"given":"Xiaozhi","family":"Li","sequence":"first","affiliation":[{"name":"Radar Technology Research Institute, School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8113-0517","authenticated-orcid":false,"given":"Zhipeng","family":"Lou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7539-3107","authenticated-orcid":false,"given":"Wei","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9099-9185","authenticated-orcid":false,"given":"Chao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Innovative Equipment Research Institute, Beijing Institute of Technology, Chengdu 610299, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"resources","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1109\/JMW.2023.3264494","article-title":"A survey on radar-based continuous human activity recognition","volume":"3","author":"Ullmann","year":"2023","journal-title":"IEEE J. Microw."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Yao, L., Chung, K.L., Tang, L., Ye, T., Wang, S., Xu, P., Bi, Y., and Wu, Y. (2026). A Hybrid Millimeter-Wave Radar\u2013Ultrasonic Fusion System for Robust Human Activity Recognition with Attention-Enhanced Deep Learning. Sensors, 26.","DOI":"10.3390\/s26031057"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3036","DOI":"10.1109\/JSYST.2022.3140546","article-title":"Noninvasive human activity recognition using millimeter-wave radar","volume":"16","author":"Yu","year":"2022","journal-title":"IEEE Syst. J."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Lin, Y., Li, H., and Faccio, D. (2024). Human multi-activities classification using mmWave radar: Feature fusion in time-domain and PCANet. Sensors, 24.","DOI":"10.3390\/s24165450"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"21730","DOI":"10.1109\/JIOT.2026.3668767","article-title":"Efficient Voxel-Based mmWave Radar HAR With Early Spatio-Temporal Fusion and a Compact 3-D-2-D Hybrid Network","volume":"13","author":"Zhao","year":"2026","journal-title":"IEEE Internet Things J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"8432","DOI":"10.1109\/TMC.2025.3649493","article-title":"mm-ARnet: Exploring Millimeter Wave Radar Point Clouds for Human Action Recognition","volume":"25","author":"Hao","year":"2026","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_7","first-page":"1","article-title":"Radar-based human activity recognition combining range\u2013time\u2013Doppler maps and range-distributed-convolutional neural networks","volume":"60","author":"Kim","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_8","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., and Wildes, R.P. (2017, January 21\u201326). Spatiotemporal multiplier networks for video action recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref_10","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., and He, K. (November, January 27). Slowfast networks for video recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"104108","DOI":"10.1016\/j.imavis.2021.104108","article-title":"Motion saliency based multi-stream multiplier ResNets for action recognition","volume":"107","author":"Zong","year":"2021","journal-title":"Image Vis. Comput."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., and Satoh, Y. (2017, January 22\u201329). Learning spatio-temporal features with 3d residual networks for action recognition. Proceedings of the IEEE International Conference on Computer Vision Workshops, Venice, Italy.","DOI":"10.1109\/ICCVW.2017.373"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yang, C., Xu, Y., Shi, J., Dai, B., and Zhou, B. (2020, January 13\u201319). Temporal pyramid network for action recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., and Ryoo, M.S. (2021, January 20\u201325). Recognizing actions in videos from unseen viewpoints. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00411"},{"key":"ref_15","first-page":"7780","article-title":"Liteeval: A coarse-to-fine framework for resource efficient video recognition","volume":"32","author":"Wu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/j.neucom.2020.05.118","article-title":"DB-LSTM: Densely-connected Bi-directional LSTM for human action recognition","volume":"444","author":"He","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.patcog.2017.10.037","article-title":"Discriminative context learning with gated recurrent unit for group activity recognition","volume":"76","author":"Kim","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., and Zisserman, A. (2019, January 15\u201320). Video action transformer network. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, X., Liu, C., Shuai, B., Zhu, Y., Brattoli, B., Chen, H., Marsic, I., and Tighe, J. (2021, January 10\u201317). Vidtr: Video transformer without convolutions. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zeng, F., Guo, M., Tan, L., Guo, F., and Liu, X. (2024). Wearable sensor-based residual multifeature fusion shrinkage networks for human activity recognition. Sensors, 24.","DOI":"10.3390\/s24030758"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"111344","DOI":"10.1016\/j.asoc.2024.111344","article-title":"Human activity recognition using a multi-branched CNN-BiLSTM-BiGRU model","volume":"154","author":"Lalwani","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1080\/03772063.2024.2402881","article-title":"1-dcnn with stacked lstm architecture for human activity recognition using wearable sensing data","volume":"71","author":"Krishnaleela","year":"2025","journal-title":"IETE J. Res."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhong, Y., Jia, H., Ding, X., and Jiang, T. (2025). Cross-Environment Device-Free Human Action Recognition via Wi-Fi Signals. Electronics, 14.","DOI":"10.3390\/electronics14112299"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chahoushi, M., Nabati, M., Asvadi, R., and Ghorashi, S.A. (2023). CSI-based human activity recognition using multi-input multi-output autoencoder and fine-tuning. Sensors, 23.","DOI":"10.3390\/s23073591"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ge, F., Dai, Z., Yang, Z., Wu, F., and Tan, L. (2024). VBCNet: A Hybird Network for Human Activity Recognition. Sensors, 24.","DOI":"10.3390\/s24237793"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wu, X., Ling, Z., Zhang, X., Ma, Z., and Deng, W. (2025). Human similar activity recognition using millimeter-wave radar based on CNN-BiLSTM and class activation mapping. Eng, 6.","DOI":"10.3390\/eng6030044"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Huan, S., Wu, L., Zhang, M., Wang, Z., and Yang, C. (2023). Radar human activity recognition with an attention-based deep learning network. Sensors, 23.","DOI":"10.3390\/s23063185"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2630","DOI":"10.1049\/rsn2.12664","article-title":"Abnormal gait recognition with millimetre-wave radar based on perceptual loss and convolutional temporal autoencoder","volume":"18","author":"Zhao","year":"2024","journal-title":"Radar Sonar Navig. IET"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zeng, X., Shi, Y., and Zhou, A. (2022). Multi-har: Human activity recognition in multi-person scenes based on mmwave sensing. Proceedings of the 2022 IEEE 8th International Conference on Computer and Communications, IEEE.","DOI":"10.1109\/ICCC56324.2022.10065810"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liu, H., Cui, K., Zhou, A., Li, W., and Ma, H. (2021). m-activity: Accurate and real-time human activity recognition via millimeter wave radar. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE.","DOI":"10.1109\/ICASSP39728.2021.9414686"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Alam, M.A.U., Rahman, M.M., and Widberg, J.Q. (2021). Palmar: Towards adaptive multi-inhabitant activity recognition in point-cloud technology. Proceedings of the IEEE INFOCOM 2021\u2014IEEE Conference on Computer Communications, IEEE.","DOI":"10.1109\/INFOCOM42981.2021.9488789"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Yan, J., Wang, Y., Xu, C., and Liu, D. (2026). OG-PCL: Efficient Sparse Radar Point Cloud Processing for Human Activity Recognition. Proceedings of the 2026 IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE.","DOI":"10.1109\/ICASSP55912.2026.11462700"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Liu, B., Li, J., Song, Z., Xia, Y., Li, P., and Fan, Q. (2024). Sparse Millimeter-wave Radar Point Clouds based Transformer for Human Activity Recognition. Proceedings of the 2024 China Automation Congress, IEEE.","DOI":"10.1109\/CAC63892.2024.10864729"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Guo, Z., Guendel, R.G., Yarovoy, A., and Fioranelli, F. (2023). Point transformer-based human activity recognition using high-dimensional radar point clouds. Proceedings of the 2023 IEEE Radar Conference, IEEE.","DOI":"10.1109\/RadarConf2351548.2023.10149679"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Yan, J., Zeng, X., Zhou, A., and Ma, H. (2022). Mm-hat: Transformer for millimeter-wave sensing based human activity recognition. Proceedings of the IEEE Global Communications Conference, IEEE.","DOI":"10.1109\/GLOBECOM48099.2022.10000673"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Chen, Y., Guo, Z., Zhang, H., and Xu, M. (2025). STPM: Spatial-Temporal Point Mamba for Activity Recognition Using mmWave Radar Point Clouds. Proceedings of the 2025 IEEE International Conference on Multimedia and Expo, IEEE.","DOI":"10.1109\/ICME59968.2025.11208900"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Gong, P., Wang, C., and Zhang, L. (2021). Mmpoint-gnn: Graph neural network with dynamic edges for human activity recognition through a millimeter-wave radar. Proceedings of the 2021 International Joint Conference on Neural Networks, IEEE.","DOI":"10.1109\/IJCNN52387.2021.9533989"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5700","DOI":"10.1109\/TMC.2025.3634221","article-title":"Exploring Spatial-Temporal Representation via Star Graph for mmWave Radar-Based Human Activity Recognition","volume":"25","author":"Gao","year":"2026","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Singh, A.D., Sandha, S.S., Garcia, L., and Srivastava, M. (2019, January 25\u201329). Radhar: Human activity recognition from point clouds generated through a millimeter-wave radar. Proceedings of the 3rd ACM Workshop on Millimeter-wave Networks and Sensing Systems, Los Cabos, Mexico.","DOI":"10.1145\/3349624.3356768"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5717\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:21:57Z","timestamp":1788949317000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5717"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":39,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26185717"],"URL":"https:\/\/doi.org\/10.3390\/s26185717","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]}}}