{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T09:09:32Z","timestamp":1779008972987,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":96,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T00:00:00Z","timestamp":1778371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,11]]},"DOI":"10.1145\/3774906.3802759","type":"proceedings-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:20:14Z","timestamp":1778250014000},"page":"488-502","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Generalizable Wireless Sensing Models via Pre-training on Multi-Source Datasets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2888-2370","authenticated-orcid":false,"given":"Chen","family":"Gong","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7226-8178","authenticated-orcid":false,"given":"Bo","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5155-451X","authenticated-orcid":false,"given":"Qihao","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2144-6960","authenticated-orcid":false,"given":"Wei","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2652-8941","authenticated-orcid":false,"given":"Yin","family":"Chen","sequence":"additional","affiliation":[{"name":"Reitaku University, Kashiwa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9718-4552","authenticated-orcid":false,"given":"Jin","family":"Nakazawa","sequence":"additional","affiliation":[{"name":"Keio University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9171-2596","authenticated-orcid":false,"given":"Chenren","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,10]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Amro Abbas Kushal Tirumala D\u00e1niel Simig Surya Ganguli and Ari\u00a0S Morcos. 2023. Semdedup: Data-efficient learning at web-scale through semantic deduplication. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.09540 (2023)."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM.2019.8767421"},{"key":"e_1_3_3_2_4_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Mohiuddin Ahmed Raihan Seraj and Syed Mohammed\u00a0Shamsul Islam. 2020. The k-means algorithm: A comprehensive survey and performance evaluation. Electronics (2020).","DOI":"10.3390\/electronics9081295"},{"key":"e_1_3_3_2_6_2","unstructured":"Arash Khoeini. 2025. InfoNCE Loss - PyTorch Implementation. https:\/\/github.com\/arashkhoeini\/infonce [Online; accessed 23-August-2025]."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Anurag Arnab Mostafa Dehghani Georg Heigold Chen Sun Mario Lu\u010di\u0107 and Cordelia Schmid. 2021. ViViT: A Video Vision Transformer. arXiv:arXiv 2103.15691","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_3_2_8_2","unstructured":"Rishi Bommasani. 2021. On the opportunities and risks of foundation models. arXiv:https:\/\/arXiv.org\/abs\/2108.07258 (2021)."},{"key":"e_1_3_3_2_9_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. NeurIPS (2020)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699331"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548262"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Fei-Long Chen Du-Zhen Zhang Ming-Lun Han Xiu-Yi Chen Jing Shi Shuang Xu and Bo Xu. 2023. Vlp: A survey on vision-language pre-training. Machine Intelligence Research (2023).","DOI":"10.1007\/s11633-022-1369-5"},{"key":"e_1_3_3_2_13_2","volume-title":"ICML","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In ICML."},{"key":"e_1_3_3_2_14_2","volume-title":"IJCAI","author":"Chen Wenxi","year":"2024","unstructured":"Wenxi Chen, Yuzhe Liang, Ziyang Ma, Zhisheng Zheng, and Xie Chen. 2024. EAT: Self-Supervised Pre-Training with Efficient Audio Transformer. In IJCAI."},{"key":"e_1_3_3_2_15_2","unstructured":"Guoxuan Chi Zheng Yang Chenshu Wu Jingao Xu Yuchong Gao Yunhao Liu and Tony\u00a0Xiao Han. 2024. RF-Diffusion: Radio Signal Generation via Time-Frequency Diffusion. ACM MobiCom (2024)."},{"key":"e_1_3_3_2_16_2","volume-title":"ACL","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In ACL."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430735"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Xuefu Dong Liqiang Xu Lixing He Zengyi Han Ken Christofferson Yifei Chen Akihito Taya Yuuki Nishiyama and Kaoru Sezaki. 2025. Poster: Recognizing Hidden-in-the-Ear Private Key for Reliable Silent Speech Interface Using Multi-Task Learning. ACM UbiComp (2025).","DOI":"10.1145\/3714394.3754429"},{"key":"e_1_3_3_2_19_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et\u00a0al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_2_20_2","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. arXiv:https:\/\/arXiv.org\/abs\/2401.08281 (2024)."},{"key":"e_1_3_3_2_21_2","volume-title":"ICML","author":"Evci Utku","year":"2022","unstructured":"Utku Evci, Vincent Dumoulin, Hugo Larochelle, and Michael\u00a0C Mozer. 2022. Head2toe: Utilizing intermediate representations for better transfer learning. In ICML."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621246"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP62071.2024.10827599"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Zijun Gao Haibao Liu and Lingbo Li. 2025. Data augmentation for time-series classification: An extensive empirical study and comprehensive survey. JAIR 83 (2025).","DOI":"10.1613\/jair.1.17084"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.56021\/9781421407944"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Chen Gong Bo Liang Wei Gao and Chenren Xu. 2025. Data Can Speak for Itself: Quality-guided Utilization of Wireless Synthetic Data. ACM MobiSys (2025).","DOI":"10.1145\/3711875.3729123"},{"key":"e_1_3_3_2_28_2","volume-title":"Interspeech","author":"Gong Yuan","year":"2021","unstructured":"Yuan Gong, Yu-An Chung, and James Glass. 2021. AST: Audio Spectrogram Transformer. In Interspeech."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"e_1_3_3_2_30_2","unstructured":"Sylvain Gugger Lysandre Debut Thomas Wolf Philipp Schmid Zachary Mueller Sourab Mangrulkar Marc Sun and Benjamin Bossan. 2022. Accelerate: Training and inference at scale made simple efficient and adaptable. https:\/\/github.com\/huggingface\/accelerate."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Jie Gui Tuo Chen Jing Zhang Qiong Cao Zhenan Sun Hao Luo and Dacheng Tao. 2024. A Survey on Self-Supervised Learning: Algorithms Applications and Future Trends. IEEE TPAMI (2024).","DOI":"10.1109\/TPAMI.2024.3415112"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_3_2_33_2","volume-title":"Springer ECCV","author":"Heo Byeongho","year":"2024","unstructured":"Byeongho Heo, Song Park, Dongyoon Han, and Sangdoo Yun. 2024. Rotary position embedding for vision transformer. In Springer ECCV."},{"key":"e_1_3_3_2_34_2","unstructured":"Indra Herdiana M\u00a0Alfin Kamal Mutia\u00a0Nur Estri et\u00a0al. 2025. A More Precise Elbow Method for Optimum K-means Clustering. arXiv:https:\/\/arXiv.org\/abs\/2502.00851 (2025)."},{"key":"e_1_3_3_2_35_2","unstructured":"Yuan-Hao Ho Jen-Hao Cheng Sheng\u00a0Yao Kuan Zhongyu Jiang Wenhao Chai Hsiang-Wei Huang Chih-Lung Lin and Jenq-Neng Hwang. 2024. RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark. arXiv:https:\/\/arXiv.org\/abs\/2407.13930 (2024)."},{"key":"e_1_3_3_2_36_2","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de\u00a0Las Casas Lisa\u00a0Anne Hendricks Johannes Welbl Aidan Clark et\u00a0al. 2022. Training compute-optimal large language models. arXiv:https:\/\/arXiv.org\/abs\/2203.15556 (2022)."},{"key":"e_1_3_3_2_37_2","unstructured":"Weiying Hou and Chenshu Wu. 2024. RFBoost: Understanding and Boosting Deep WiFi Sensing via Physical Data Augmentation. ACM IMWUT (2024)."},{"key":"e_1_3_3_2_38_2","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv 2021. arXiv:https:\/\/arXiv.org\/abs\/2106.09685 (2021)."},{"key":"e_1_3_3_2_39_2","unstructured":"Kaixuan Huang Yuqing Wang Molei Tao and Tuo Zhao. 2020. Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks?\u2014A Neural Tangent Kernel Perspective. NeurIPS (2020)."},{"key":"e_1_3_3_2_40_2","unstructured":"Jonathan Hui. [n. d.]. mAP (mean Average Precision) for Object Detection. https:\/\/jonathan-hui.medium.com\/map-mean-average-precision-for-object-detection-45c121a31173. [Online; accessed 31-August-2025]."},{"key":"e_1_3_3_2_41_2","unstructured":"Jeff Johnson Matthijs Douze and Herv\u00e9 J\u00e9gou. 2019. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data (2019)."},{"key":"e_1_3_3_2_42_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom\u00a0B Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling laws for neural language models. arXiv:https:\/\/arXiv.org\/abs\/2001.08361 (2020)."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699325"},{"key":"e_1_3_3_2_44_2","unstructured":"Saurabh Kataria Yi Wu Zhaoliang Chen Hyunjung\u00a0Gloria Kwak Yuhao Xu Lovely\u00a0Yeswanth Panchumarthi Ran Xiao Jiaying Lu Ayca Ermis Anni Zhao Runze Yan Alex Federov Zewen Liu Xu Wu Wei Jin Carl Yang Jocelyn Grunwell Stephanie\u00a0R. Brown Amit Shah Craig\u00a0S. Jabaley Tim Buchman Sivasubramanium\u00a0V. Bhavani Randall\u00a0J. Lee and Xiao Hu. 2025. Generalist vs Specialist Time Series Foundation Models: Investigating Potential Emergent Behaviors in Assessing Human Health Using PPG Signals."},{"key":"e_1_3_3_2_45_2","unstructured":"Prannay Khosla Piotr Teterwak Chen Wang Aaron Sarna Yonglong Tian Phillip Isola Aaron Maschinot Ce Liu and Dilip Krishnan. 2020. Supervised contrastive learning. NeurIPS (2020)."},{"key":"e_1_3_3_2_46_2","unstructured":"Ruiqi Kong and He Chen. 2025. CIRSense: Rethinking WiFi Sensing with Channel Impulse Response. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.11374 (2025)."},{"key":"e_1_3_3_2_47_2","unstructured":"Katherine Lee Daphne Ippolito Andrew Nystrom Chiyuan Zhang Douglas Eck Chris Callison-Burch and Nicholas Carlini. 2021. Deduplicating training data makes language models better. arXiv:https:\/\/arXiv.org\/abs\/2107.06499 (2021)."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00567"},{"key":"e_1_3_3_2_49_2","unstructured":"Chenning Li Zhichao Cao and Yunhao Liu. 2021. Deep AI Enabled Ubiquitous Wireless Sensing. ACM CSUR (2021)."},{"key":"e_1_3_3_2_50_2","unstructured":"Chunyuan Li Zhe Gan Zhengyuan Yang Jianwei Yang Linjie Li Lijuan Wang and Jianfeng Gao. 2023. Multimodal Foundation Models: From Specialists to General-Purpose Assistants. Found. Trends Comput. Graph. Vis. (2023)."},{"key":"e_1_3_3_2_51_2","unstructured":"Shengqiang Li Menglong Xu and Xiao-Lei Zhang. 2021. Conformer-based End-to-end Speech Recognition With Rotary Position Embedding. APSIPA ASC (2021)."},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00116"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10001175"},{"key":"e_1_3_3_2_54_2","unstructured":"Yadong Li Dongheng Zhang Jinbo Chen Jinwei Wan Dong Zhang Yang Hu Qibin Sun and Yan Chen. 2022. Towards Domain-Independent and Real-Time Gesture Recognition Using Mmwave Signal. IEEE Transactions on Mobile Computing (2022)."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"crossref","unstructured":"Yang Liu Feng Wang Naiyan Wang and Zhao-Xiang Zhang. 2023. Echoes beyond points: Unleashing the power of raw radar data in multi-modality fusion. NeurIPS (2023).","DOI":"10.52202\/075280-2347"},{"key":"e_1_3_3_2_56_2","unstructured":"Yongsen Ma Gang Zhou Shuangquan Wang Hongyang Zhao and Woosub Jung. 2018. SignFi: Sign language recognition using WiFi. ACM IMWUT (2018)."},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Yimin Mao Zhengxin Guo Biyun Sheng Linqing Gui and Fu Xiao. 2024. Wi-Cro: WiFi-Based Cross Domain Activity Recognition via Modified GAN. IEEE TVT (2024).","DOI":"10.1109\/TVT.2024.3404452"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Sai Munikoti Ian Stewart Sameera Horawalavithana Henry Kvinge Tegan\u00a0H. Emerson Sandra\u00a0E Thompson and Karl Pazdernik. 2024. Generalist Multimodal AI: A Review of Architectures Challenges and Opportunities. ArXiv (2024).","DOI":"10.2139\/ssrn.5732150"},{"key":"e_1_3_3_2_59_2","unstructured":"OECD.AI. 2025. Mean Per Joint Position Error (MPJPE). https:\/\/oecd.ai\/en\/catalogue\/metrics\/mean-per-joint-position-error-mpjpe [Online; accessed 20-August-2025]."},{"key":"e_1_3_3_2_60_2","unstructured":"Aaron van\u00a0den Oord Yazhe Li and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv:https:\/\/arXiv.org\/abs\/1807.03748 (2018)."},{"key":"e_1_3_3_2_61_2","unstructured":"OpenAI. 2025. CLIP input image size. https:\/\/github.com\/openai\/CLIP\/issues\/379 [Online; accessed 24-August-2025]."},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560519"},{"key":"e_1_3_3_2_63_2","unstructured":"Aldo Pareja Nikhil\u00a0Shivakumar Nayak Hao Wang Krishnateja Killamsetty Shivchander Sudalairaj Wenlong Zhao Seungwook Han Abhishek Bhandwaldar Guangxuan Xu Kai Xu et\u00a0al. 2024. Unveiling the secret recipe: A guide for supervised fine-tuning small llms. arXiv:https:\/\/arXiv.org\/abs\/2412.13337 (2024)."},{"key":"e_1_3_3_2_64_2","volume-title":"Digital communications","author":"Proakis John\u00a0G","year":"2001","unstructured":"John\u00a0G Proakis and Masoud Salehi. 2001. Digital communications. McGraw-hill New York."},{"key":"e_1_3_3_2_65_2","volume-title":"ICML","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In ICML."},{"key":"e_1_3_3_2_66_2","unstructured":"Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter\u00a0J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR (2020)."},{"key":"e_1_3_3_2_67_2","unstructured":"Karthik Ramasubramanian. 2017. mmWave radar for automotive and industrial applications. Texas Instruments (2017)."},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"crossref","unstructured":"Ruiyuan Song Zhi Lu Dongheng Zhang Liang Fang Zhi Wu Yang Hu Qibin Sun and Yan Chen. 2025. Unleashing the Potential of Self-Supervised RF Learning With Group Shuffle. IEEE TMC (2025).","DOI":"10.1109\/TMC.2024.3497972"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560529"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"crossref","unstructured":"Ruiyuan Song Dongheng Zhang Zhi Wu Cong Yu Chunyang Xie Shuai Yang Yang Hu and Yan Chen. 2025. RF-URL 2.0: A General Unsupervised Representation Learning Method for RF Sensing. IEEE TPAMI (2025).","DOI":"10.1109\/TPAMI.2025.3587718"},{"key":"e_1_3_3_2_71_2","unstructured":"Jianlin Su Murtadha Ahmed Yu Lu Shengfeng Pan Wen Bo and Yunfeng Liu. 2024. Roformer: Enhanced transformer with rotary position embedding. Elsevier Neurocomputing (2024)."},{"key":"e_1_3_3_2_72_2","unstructured":"TensorFlow. 2025. C4 Dataset. https:\/\/www.tensorflow.org\/datasets\/catalog\/c4 [Online; accessed 22-August-2025]."},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807213"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"crossref","unstructured":"Fei Wang Yizhe Lv Mengdie Zhu Han Ding and Jinsong Han. 2024. XRF55: A Radio Frequency Dataset for Human Indoor Action Analysis. ACM IMWUT (2024).","DOI":"10.1145\/3643543"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/2789168.2790093"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699349"},{"key":"e_1_3_3_2_78_2","unstructured":"Wikipedia Contributors. 2025. Constant false alarm rate. https:\/\/en.wikipedia.org\/wiki\/Constant_false_alarm_rate [Online; accessed 23-August-2025]."},{"key":"e_1_3_3_2_79_2","unstructured":"Bichen Wu Chenfeng Xu Xiaoliang Dai Alvin Wan Peizhao Zhang Zhicheng Yan Masayoshi Tomizuka Joseph Gonzalez Kurt Keutzer and Peter Vajda. 2020. Visual Transformers: Token-based Image Representation and Processing for Computer Vision. arXiv:arXiv 2006.03677"},{"key":"e_1_3_3_2_80_2","unstructured":"Chaoyi Wu Xiaoman Zhang Ya Zhang Hui Hui Yanfeng Wang and Weidi Xie. 2025. Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data. Nature Communications (2025)."},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"crossref","unstructured":"Chunjing Xiao Daojun Han Yongsen Ma and Zhiguang Qin. 2019. CsiGAN: Robust channel state information-based activity recognition with GANs. IEEE IoTJ (2019).","DOI":"10.1109\/JIOT.2019.2936580"},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"crossref","unstructured":"Rui Xiao Jianwei Liu Jinsong Han and Kui Ren. 2021. OneFi: One-Shot Recognition for Unseen Gesture via COTS WiFi. ACM SenSys (2021).","DOI":"10.1145\/3485730.3485936"},{"key":"e_1_3_3_2_83_2","unstructured":"Zhenda Xie Zigang Geng Jingcheng Hu Zheng Zhang Han Hu and Yue Cao. 2022. Revealing the Dark Secrets of Masked Image Modeling. IEEE\/CVF CVPR (2022)."},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"crossref","unstructured":"Jianfei Yang Xinyan Chen Han Zou Chris\u00a0Xiaoxuan Lu Dazhuo Wang Sumei Sun and Lihua Xie. 2023. SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing. Patterns (2023).","DOI":"10.1016\/j.patter.2023.100703"},{"key":"e_1_3_3_2_85_2","doi-asserted-by":"crossref","unstructured":"Jianfei Yang Xinyan Chen Han Zou Dazhuo Wang and Lihua Xie. 2022. Autofi: Toward automatic wi-fi human sensing via geometric self-supervised learning. IEEE Internet of Things Journal 10 8 (2022) 7416\u20137425.","DOI":"10.1109\/JIOT.2022.3228820"},{"key":"e_1_3_3_2_86_2","unstructured":"Jianfei Yang He Huang Yunjiao Zhou Xinyan Chen Yuecong Xu Shenghai Yuan Han Zou Chris\u00a0Xiaoxuan Lu and Lihua Xie. 2023. Mm-fi: Multi-modal non-intrusive 4d human dataset for versatile wireless sensing. NeurIPS (2023)."},{"key":"e_1_3_3_2_87_2","unstructured":"Yuchong Yao Nandakishor Desai and Marimuthu Palaniswami. 2022. Masked contrastive representation learning. arXiv:https:\/\/arXiv.org\/abs\/2211.06012 (2022)."},{"key":"e_1_3_3_2_88_2","unstructured":"Shukang Yin Chaoyou Fu Sirui Zhao Ke Li Xing Sun Tong Xu and Enhong Chen. 2024. A survey on multimodal large language models. National Science Review (2024)."},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/CRV52889.2021.00021"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241570"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"crossref","unstructured":"Jia Zhang Rui Xi Yuan He Yimiao Sun Xiuzhen Guo Weiguo Wang Xin Na Yunhao Liu Zhenguo Shi and Tao Gu. 2023. A survey of mmWave-based human sensing: Technology platforms and applications. IEEE Communications Surveys & Tutorials (2023).","DOI":"10.1109\/COMST.2023.3298300"},{"key":"e_1_3_3_2_92_2","unstructured":"Xie Zhang Chengpei Tang Yasong An and Kang Yin. 2021. WiFi-based Multi-task Sensing. ArXiv (2021)."},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"crossref","unstructured":"Yi Zhang Yue Zheng Kun Qian Guidong Zhang Yunhao Liu Chenshu Wu and Zheng Yang. 2021. Widar3. 0: Zero-effort cross-domain gesture recognition with Wi-Fi. IEEE TPAMI (2021).","DOI":"10.1109\/TPAMI.2021.3105387"},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592527"},{"key":"e_1_3_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01072"},{"key":"e_1_3_3_2_96_2","unstructured":"Guozhen Zhu Yuqian Hu Weihang Gao Wei-Hsiang Wang Beibei Wang and KJ Liu. 2025. CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing. arXiv:https:\/\/arXiv.org\/abs\/2505.21866 (2025)."},{"key":"e_1_3_3_2_97_2","unstructured":"Guozhen Zhu Yuqian Hu Sakila Jayaweera Weihang Gao Wei-Hsiang Wang Jiaxuan Zhang Beibei Wang Chenshu Wu and KJ Liu. 2026. AM-FM: A Foundation Model for Ambient Intelligence Through WiFi. arXiv:https:\/\/arXiv.org\/abs\/2602.11200 (2026)."}],"event":{"name":"SenSys '26: ACM\/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems","location":"Saint Malo France","acronym":"SenSys '26","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","IEEE CS"]},"container-title":["Proceedings of the 2026 ACM\/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774906.3802759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T08:32:16Z","timestamp":1779006736000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774906.3802759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,10]]},"references-count":96,"alternative-id":["10.1145\/3774906.3802759","10.1145\/3774906"],"URL":"https:\/\/doi.org\/10.1145\/3774906.3802759","relation":{},"subject":[],"published":{"date-parts":[[2026,5,10]]},"assertion":[{"value":"2026-05-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}