{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:41:41Z","timestamp":1775666501043,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T00:00:00Z","timestamp":1746489600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,6]]},"DOI":"10.1145\/3722567.3727849","type":"proceedings-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T06:20:31Z","timestamp":1745389231000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Inference of parallel partitioned hybrid-Vision Transformers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8343-9649","authenticated-orcid":false,"given":"Oscar Artur Bernd","family":"Berg","sequence":"first","affiliation":[{"name":"TU Wien, Vienna, Austria and Mid Sweden University, Sundsvall, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9903-1338","authenticated-orcid":false,"given":"Eiraj","family":"Saqib","sequence":"additional","affiliation":[{"name":"Mid Sweden University, Sundsvall, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2251-0004","authenticated-orcid":false,"given":"Axel","family":"Jantsch","sequence":"additional","affiliation":[{"name":"TU Wien, Vienna, Austria and Mid Sweden University, Sundsvall, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8607-4083","authenticated-orcid":false,"given":"Mattias","family":"O'Nils","sequence":"additional","affiliation":[{"name":"Mid Sweden University, Sundsvall, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0282-5471","authenticated-orcid":false,"given":"Silvia","family":"Krug","sequence":"additional","affiliation":[{"name":"Mid Sweden University, Ilmenau, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3774-4850","authenticated-orcid":false,"given":"Irida","family":"Shallari","sequence":"additional","affiliation":[{"name":"Mid Sweden University, Sundsvall, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3351-0491","authenticated-orcid":false,"given":"Isaac S\u00e1nchez","family":"Leal","sequence":"additional","affiliation":[{"name":"Mid Sweden University, Sundsvall, Sweden"}]}],"member":"320","published-online":{"date-parts":[[2025,5,6]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, and Yuxiong He.","author":"Aminabadi Reza Yazdani","year":"2022","unstructured":"Reza Yazdani Aminabadi, Samyam Rajbhandari, Minjia Zhang, Ammar Ahmad Awan, Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, and Yuxiong He. 2022. DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale. arXiv:2207.00032 [cs.LG] https:\/\/arxiv.org\/abs\/2207.00032"},{"key":"e_1_3_2_1_2_1","unstructured":"IoT Analytics. 2024. State of IoT 2024: Number of connected IoT devices growing 13% to 18.8 billion globally. https:\/\/iot-analytics.com\/state-of-iot-2024-number-of-connected-iot-devices\/. Accessed: 2024-12-10."},{"key":"e_1_3_2_1_3_1","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:2103.15691 [cs.CV] https:\/\/arxiv.org\/abs\/2103.15691","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Severin Bochem Victor J. B. Jung Arpan Prasad Francesco Conti and Luca Benini. 2024. Distributed Inference with Minimal Off-Chip Traffic for Transformers on Low-Power MCUs. arXiv:2412.04372 [cs.AR] https:\/\/arxiv.org\/abs\/2412.04372","DOI":"10.23919\/DATE64628.2025.10992712"},{"key":"e_1_3_2_1_5_1","unstructured":"Zihang Dai Hanxiao Liu Quoc V. Le and Mingxing Tan. 2021. CoAtNet: Marrying Convolution and Attention for All Data Sizes. arXiv:2106.04803 [cs.CV] https:\/\/arxiv.org\/abs\/2106.04803"},{"key":"e_1_3_2_1_6_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv:2010.11929 [cs.CV] https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Amir Erfan Eshratifar Amirhossein Esmaili and Massoud Pedram. 2019. BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services. arXiv:1902.01000 [cs.DC] https:\/\/arxiv.org\/abs\/1902.01000","DOI":"10.1109\/ISLPED.2019.8824955"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2972000"},{"key":"e_1_3_2_1_9_1","volume-title":"Dally","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William J. Dally. 2016. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. arXiv:1510.00149 [cs.CV] https:\/\/arxiv.org\/abs\/1510.00149"},{"key":"e_1_3_2_1_10_1","volume-title":"When the Edge Meets Transformers: Distributed Inference with Transformer Models. In 2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS). IEEE, 82--92","author":"Hu Chenghao","year":"2024","unstructured":"Chenghao Hu and Baochun Li. 2024. When the Edge Meets Transformers: Distributed Inference with Transformer Models. In 2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS). IEEE, 82--92."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3234761"},{"key":"e_1_3_2_1_12_1","volume-title":"Weinberger (Eds.)","volume":"25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems, F. Pereira, C.J. Burges, L. Bottou, and K.Q. Weinberger (Eds.), Vol. 25. Curran Associates, Inc."},{"key":"e_1_3_2_1_13_1","unstructured":"Yanyu Li Geng Yuan Yang Wen Ju Hu Georgios Evangelidis Sergey Tulyakov Yanzhi Wang and Jian Ren. 2022. EfficientFormer: Vision Transformers at MobileNet Speed. arXiv:2206.01191 [cs.CV] https:\/\/arxiv.org\/abs\/2206.01191"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3657282"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Yoshitomo Matsubara Davide Callegaro Sameer Singh Marco Levorato and Francesco Restuccia. 2022. BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing. In 2022 IEEE 23rd International Symposium on a World of Wireless Mobile and Multimedia Networks (WoWMoM). IEEE 337--346. doi:10.1109\/wowmom54355.2022.00032","DOI":"10.1109\/wowmom54355.2022.00032"},{"key":"e_1_3_2_1_16_1","unstructured":"Junting Pan Adrian Bulat Fuwen Tan Xiatian Zhu Lukasz Dudziak Hongsheng Li Georgios Tzimiropoulos and Brais Martinez. 2022. EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers. arXiv:2205.03436 [cs.CV] https:\/\/arxiv.org\/abs\/2205.03436"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"John Shen and Harideep Nair. 2023. Cortical Columns Computing Systems: Microarchitecture Model Functional Building Blocks and Design Tools. doi:10.5772\/intechopen.110252","DOI":"10.5772\/intechopen.110252"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Jiwei Yang Xu Shen Jun Xing Xinmei Tian Houqiang Li Bing Deng Jianqiang Huang and Xiansheng Hua. 2019. Quantization Networks. arXiv:1911.09464 [cs.CV] https:\/\/arxiv.org\/abs\/1911.09464","DOI":"10.1109\/CVPR.2019.00748"},{"key":"e_1_3_2_1_19_1","unstructured":"Liekang Zeng Xu Chen Zhi Zhou Lei Yang and Junshan Zhang. 2020. CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices. arXiv:2012.03257 [cs.NI] https:\/\/arxiv.org\/abs\/2012.03257"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858384"}],"event":{"name":"SenSys '25: The 23rd ACM Conference on Embedded Networked Sensor Systems","location":"Irvine CA USA","acronym":"SenSys '25","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems","SIGBED ACM Special Interest Group on Embedded Systems","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 4th International Workshop on Real-time and IntelliGent Edge computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3722567.3727849","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3722567.3727849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:44:50Z","timestamp":1755974690000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3722567.3727849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,6]]},"references-count":20,"alternative-id":["10.1145\/3722567.3727849","10.1145\/3722567"],"URL":"https:\/\/doi.org\/10.1145\/3722567.3727849","relation":{},"subject":[],"published":{"date-parts":[[2025,5,6]]},"assertion":[{"value":"2025-05-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}