{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:52:09Z","timestamp":1792515129036,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583205","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T19:30:25Z","timestamp":1682537425000},"page":"1437-1445","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":52,"title":["FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9873-7681","authenticated-orcid":false,"given":"Mingyue","family":"Cheng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, China and State Key Laboratory of Cognitive Intelligence, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-5550","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China and State Key Laboratory of Cognitive Intelligence, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0994-473X","authenticated-orcid":false,"given":"Zhiding","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China and State Key Laboratory of Cognitive Intelligence, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8061-7486","authenticated-orcid":false,"given":"Zhi","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0685-0834","authenticated-orcid":false,"given":"Yucong","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China and State Key Laboratory of Cognitive Intelligence, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-4102","authenticated-orcid":false,"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China and State Key Laboratory of Cognitive Intelligence, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Thomas Bachlechner Bodhisattwa\u00a0Prasad Majumder Henry Mao Gary Cottrell and Julian McAuley. 2021. Rezero is all you need: Fast convergence at large depth. In Uncertainty in Artificial Intelligence. PMLR 1352\u20131361."},{"key":"e_1_3_2_1_2_1","volume-title":"Michael Flynn, James Large, Aaron Bostrom, Paul Southam, and Eamonn Keogh.","author":"Bagnall Anthony","year":"2018","unstructured":"Anthony Bagnall, Hoang\u00a0Anh Dau, Jason Lines, Michael Flynn, James Large, Aaron Bostrom, Paul Southam, and Eamonn Keogh. 2018. The UEA multivariate time series classification archive, 2018. arXiv preprint arXiv:1811.00075 (2018)."},{"key":"e_1_3_2_1_3_1","volume-title":"Aaron Bostrom, James Large, and Eamonn Keogh.","author":"Bagnall Anthony","year":"2017","unstructured":"Anthony Bagnall, Jason Lines, Aaron Bostrom, James Large, and Eamonn Keogh. 2017. The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data mining and knowledge discovery 31, 3 (2017), 606\u2013660."},{"key":"e_1_3_2_1_4_1","volume-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271","author":"Bai Shaojie","year":"2018","unstructured":"Shaojie Bai, J\u00a0Zico Kolter, and Vladlen Koltun. 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.01.001"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512066"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462863"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00015"},{"key":"e_1_3_2_1_9_1","volume-title":"Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882","author":"Chu Xiangxiang","year":"2021","unstructured":"Xiangxiang Chu, Zhi Tian, Bo Zhang, Xinlong Wang, Xiaolin Wei, Huaxia Xia, and Chunhua Shen. 2021. Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)."},{"key":"e_1_3_2_1_10_1","unstructured":"Jonathan Crabb\u00e9 and Mihaela Van Der\u00a0Schaar. 2021. Explaining time series predictions with dynamic masks. In ICML. PMLR 2166\u20132177."},{"key":"e_1_3_2_1_11_1","volume-title":"Multi-scale convolutional neural networks for time series classification. arXiv preprint arXiv:1603.06995","author":"Cui Zhicheng","year":"2016","unstructured":"Zhicheng Cui, Wenlin Chen, and Yixin Chen. 2016. Multi-scale convolutional neural networks for time series classification. arXiv preprint arXiv:1603.06995 (2016)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00701-z"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467231"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248548"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.07.032"},{"key":"e_1_3_2_1_16_1","unstructured":"Ge Gao Qitong Gao Xi Yang Miroslav Pajic and Min Chi. [n. d.]. A Reinforcement Learning-Informed Pattern Mining Framework for Multivariate Time Series Classification. ([n. d.])."},{"key":"e_1_3_2_1_17_1","volume-title":"R2n2: Residual recurrent neural networks for multivariate time series forecasting. arXiv preprint arXiv:1709.03159","author":"Goel Hardik","year":"2017","unstructured":"Hardik Goel, Igor Melnyk, and Arindam Banerjee. 2017. R2n2: Residual recurrent neural networks for multivariate time series forecasting. arXiv preprint arXiv:1709.03159 (2017)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Josif Grabocka Nicolas Schilling Martin Wistuba and Lars Schmidt-Thieme. 2014. Learning time-series shapelets. In ACM SIGKDD. 392\u2013401.","DOI":"10.1145\/2623330.2623613"},{"key":"e_1_3_2_1_19_1","volume-title":"Deep residual learning for image recognition","author":"He Kaiming","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In IEEE CVPR. 770\u2013778."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512056"},{"key":"e_1_3_2_1_21_1","volume-title":"How much position information do convolutional neural networks encode?arXiv preprint arXiv:2001.08248","author":"Islam Md\u00a0Amirul","year":"2020","unstructured":"Md\u00a0Amirul Islam, Sen Jia, and Neil\u00a0DB Bruce. 2020. How much position information do convolutional neural networks encode?arXiv preprint arXiv:2001.08248 (2020)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00619-1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00710-y"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.04.014"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339579"},{"key":"e_1_3_2_1_26_1","volume-title":"Gated transformer networks for multivariate time series classification. arXiv preprint arXiv:2103.14438","author":"Liu Minghao","year":"2021","unstructured":"Minghao Liu, Shengqi Ren, Siyuan Ma, Jiahui Jiao, Yizhou Chen, Zhiguang Wang, and Wei Song. 2021. Gated transformer networks for multivariate time series classification. arXiv preprint arXiv:2103.14438 (2021)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00039"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06057-9"},{"key":"e_1_3_2_1_29_1","volume-title":"Machine Learning for Healthcare Conference. PMLR, 332\u2013347","author":"Oh Jeeheh","year":"2018","unstructured":"Jeeheh Oh, Jiaxuan Wang, and Jenna Wiens. 2018. Learning to exploit invariances in clinical time-series data using sequence transformer networks. In Machine Learning for Healthcare Conference. PMLR, 332\u2013347."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20040969"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00727-3"},{"key":"e_1_3_2_1_32_1","volume-title":"Self-attention for raw optical satellite time series classification. ISPRS journal of photogrammetry and remote sensing 169","author":"Ru\u00dfwurm Marc","year":"2020","unstructured":"Marc Ru\u00dfwurm and Marco K\u00f6rner. 2020. Self-attention for raw optical satellite time series classification. ISPRS journal of photogrammetry and remote sensing 169 (2020), 421\u2013435."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3014842"},{"key":"e_1_3_2_1_34_1","volume-title":"Multivariate time series classification with WEASEL+ MUSE. arXiv preprint arXiv:1711.11343","author":"Sch\u00e4fer Patrick","year":"2017","unstructured":"Patrick Sch\u00e4fer and Ulf Leser. 2017. Multivariate time series classification with WEASEL+ MUSE. arXiv preprint arXiv:1711.11343 (2017)."},{"key":"e_1_3_2_1_35_1","volume-title":"Financial time series forecasting with deep learning: A systematic literature review: 2005\u20132019. Applied soft computing 90","author":"Sezer Omer\u00a0Berat","year":"2020","unstructured":"Omer\u00a0Berat Sezer, Mehmet\u00a0Ugur Gudelek, and Ahmet\u00a0Murat Ozbayoglu. 2020. Financial time series forecasting with deep learning: A systematic literature review: 2005\u20132019. Applied soft computing 90 (2020), 106181."},{"key":"e_1_3_2_1_36_1","volume-title":"MultiRocket: multiple pooling operators and transformations for fast and effective time series classification. DMKD","author":"Tan Chang\u00a0Wei","year":"2022","unstructured":"Chang\u00a0Wei Tan, Angus Dempster, Christoph Bergmeir, and Geoffrey\u00a0I Webb. 2022. MultiRocket: multiple pooling operators and transformations for fast and effective time series classification. DMKD (2022), 1\u201324."},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Learning Representations.","author":"Tang Wensi","year":"2021","unstructured":"Wensi Tang, Guodong Long, Lu Liu, Tianyi Zhou, Michael Blumenstein, and Jing Jiang. 2021. Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_38_1","volume-title":"Efficient transformers: A survey. ACM Computing Surveys (CSUR)","author":"Tay Yi","year":"2020","unstructured":"Yi Tay, Mostafa Dehghani, Dara Bahri, and Donald Metzler. 2020. Efficient transformers: A survey. ACM Computing Surveys (CSUR) (2020)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449945"},{"key":"e_1_3_2_1_40_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_41_1","volume-title":"Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768","author":"Wang Sinong","year":"2020","unstructured":"Sinong Wang, Belinda\u00a0Z Li, Madian Khabsa, Han Fang, and Hao Ma. 2020. Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)."},{"key":"e_1_3_2_1_42_1","volume-title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","author":"Wang Wenhai","unstructured":"Wenhai Wang and Enze at\u00a0al Xie. 2021. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In IEEE\/CVF ICCV. 568\u2013578."},{"key":"e_1_3_2_1_43_1","volume-title":"Transformers in time series: A survey. arXiv preprint arXiv:2202.07125","author":"Wen Qingsong","year":"2022","unstructured":"Qingsong Wen, Tian Zhou, Chaoli Zhang, Weiqi Chen, Ziqing Ma, Junchi Yan, and Liang Sun. 2022. Transformers in time series: A survey. arXiv preprint arXiv:2202.07125 (2022)."},{"key":"e_1_3_2_1_44_1","volume-title":"Flowformer: Linearizing Transformers with Conservation Flows. In International Conference on Machine Learning.","author":"Wu Haixu","year":"2022","unstructured":"Haixu Wu, Jialong Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2022. Flowformer: Linearizing Transformers with Conservation Flows. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403118"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557122"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2016.07.017"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467401"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6165"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08010-9_33"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583205","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T14:09:18Z","timestamp":1750169358000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":51,"alternative-id":["10.1145\/3543507.3583205","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583205","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}