{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:17:46Z","timestamp":1771467466040,"version":"3.50.1"},"reference-count":169,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Research Program Human\u2013Computer-Interaction through the Project \u201cchreibtrainer\u201d","award":["16SV8228"],"award-info":[{"award-number":["16SV8228"]}]},{"name":"Bavarian Ministry for Economic Affairs, Infrastructure, Transport and Technology through the Center for Analytics-Data-Applications (ADA-Center) within the Framework of \u201cBAYERN DIGITAL II.\u201d"},{"name":"Federal Ministry of Education and Research (BMBF) of Germany","award":["01IS18036A"],"award-info":[{"award-number":["01IS18036A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3310819","type":"journal-article","created":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T17:39:52Z","timestamp":1693503592000},"page":"94148-94172","source":"Crossref","is-referenced-by-count":13,"title":["Auxiliary Cross-Modal Representation Learning With Triplet Loss Functions for Online Handwriting Recognition"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4392-0830","authenticated-orcid":false,"given":"Felix","family":"Ott","sequence":"first","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits, Nuremberg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8772-9202","authenticated-orcid":false,"given":"David","family":"R\u00fcgamer","sequence":"additional","affiliation":[{"name":"LMU Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3698","authenticated-orcid":false,"given":"Lucas","family":"Heublein","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits, Nuremberg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6002-6980","authenticated-orcid":false,"given":"Bernd","family":"Bischl","sequence":"additional","affiliation":[{"name":"LMU Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8108-0230","authenticated-orcid":false,"given":"Christopher","family":"Mutschler","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits, Nuremberg, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2705068"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00684"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.466"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2879846"},{"key":"ref6","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Faghri"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref8","first-page":"8996","article-title":"Neural multisensory scene inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"32","author":"Lim"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103352"},{"key":"ref10","first-page":"2023","article-title":"Learning using privileged information: Similarity control and knowledge transfer","volume-title":"J. Mach. Learn. Res.","volume":"16","author":"Vapnik"},{"key":"ref11","volume-title":"Understanding LUPI (Learning Using Privileged Information)","author":"Momeni","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01065"},{"key":"ref14","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"Proc. ICML","author":"Long"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548167"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3550316"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3517246"},{"key":"ref19","first-page":"19174","article-title":"AlignMixup: Improving representations by interpolating aligned features","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Venkataramanan"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413091"},{"key":"ref21","article-title":"Triplet is all you need with random mappings for unsupervised visual representation learning","author":"Li","year":"2021","journal-title":"arXiv:2107.10419"},{"key":"ref22","first-page":"3235","article-title":"Proxy anchor loss for deep metric learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Kim"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9599"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207185"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00254"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"issue":"1","key":"ref28","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.asej.2010.09.007","article-title":"Online signature verification and handwriting classification","volume":"1","author":"Fahmy","year":"2010","journal-title":"J. Ain Shams Eng."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/34.824821"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.1997.620583"},{"key":"ref31","article-title":"Motion-based handwriting recognition","author":"Kevin Chen","year":"2021","journal-title":"arXiv:2101.06022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173705"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2991\/cse.2013.52"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2014.2365723"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3411842"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00131"},{"key":"ref37","first-page":"1","article-title":"Uncertainty-aware evaluation of time-series classification for online handwriting recognition with domain shift","volume-title":"Proc. IJCAI-ECAI Intl. Workshop Spatio-Temporal Reasoning Learn. (STRL)","volume":"3190","author":"Kla\u00df"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-022-00415-6"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227781"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00438"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01472"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-015-0102-5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2008.04.003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116480"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR.2014.30"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333780"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.141"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.253"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-8697-2_32"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114004"},{"key":"ref52","first-page":"1","article-title":"An efficient end-to-end neural model for handwritten text recognition","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Chowdhury"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.02.008"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00013"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00208"},{"key":"ref56","first-page":"545","article-title":"Offline handwriting recognition with multidimensional recurrent neural networks","volume-title":"Proc. 21st Int. Conf. Neural Inf. Process. Syst.","author":"Graves"},{"key":"ref57","first-page":"838","article-title":"Joint line segmentation and transcription for end-to-end handwritten paragraph recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Bluche"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR.2016.0052"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.92"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.174"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR-2018.2018.00031"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2018.70"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108766"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR.2014.55"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.137"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.20"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.111"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2606"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-018-0295-0"},{"key":"ref70","article-title":"Efficient character-level document classification by combining convolution and recurrent layers","author":"Xiao","year":"2016","journal-title":"arXiv:1602.00367"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-020-00350-4"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/495"},{"key":"ref73","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107482","article-title":"Accurate, data-efficient, unconstrained text recognition with convolutional neural networks","volume":"108","author":"Yousef","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref75","article-title":"Generative adversarial network for handwritten text","author":"Ji","year":"2019","journal-title":"arXiv:1907.11845"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173779"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/2886099"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00083"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/8507706"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3494956"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICET55676.2022.9824489"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104198"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1021\/acsami.2c13714"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.3390\/s22207840"},{"key":"ref85","first-page":"1","article-title":"Hardware-aware workload distribution for AI-based online handwriting recognition in a sensor pen","volume-title":"Proc. Medit. Conf. Embedded Comput. (MECO)","author":"Kre\u00df"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37660-3_26"},{"key":"ref87","article-title":"Detecting handwritten mathematical terms with sensor based data","author":"Wegmeth","year":"2021","journal-title":"arXiv:2109.05594"},{"key":"ref88","first-page":"1","article-title":"A pen is all you need","volume-title":"Proc. 20th Student Conf. IT","author":"Bronkhorst"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86334-0_4"},{"key":"ref90","article-title":"Improving accuracy and explainability of online handwriting recognition","author":"Azimi","year":"2022","journal-title":"arXiv:2209.09102"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref92","article-title":"Beyond just vision: A review on self-supervised representation learning on multimodal and temporal data","author":"Deldari","year":"2022","journal-title":"arXiv:2206.02353"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548411"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.70"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2005.202"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01240"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.307"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413540"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/106"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/3387164"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104003"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.560"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019185"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953194"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548263"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548397"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_41"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50832-0_60"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.07737"},{"key":"ref112","first-page":"1473","article-title":"Distance metric learning for large margin nearest neighbor classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Weinberger"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref114","first-page":"3939","article-title":"Imaging time-series to improve classification and imputation","volume-title":"Proc. 24th Int. Conf. Artif. Intell. (IJCAI)","author":"Wang"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2005.132"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref117","first-page":"1","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Intl. Conf. Learn. Represent. (ICLR)","author":"Brock","year":"2019"},{"key":"ref118","article-title":"Geometric GAN","author":"Lim","year":"2017","journal-title":"arXiv:1705.02894"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276390"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.110"},{"key":"ref123","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00710-y"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_18"},{"issue":"12","key":"ref126","doi-asserted-by":"crossref","first-page":"8846","DOI":"10.1109\/TPAMI.2021.3122572","article-title":"Content and style aware generation of text-line images for handwriting recognition","volume":"44","author":"Kang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref127","article-title":"SLOGAN: Handwriting style synthesis for arbitrary-length and out-of-vocabulary text","author":"Luo","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3550070"},{"issue":"4","key":"ref129","first-page":"3422","article-title":"HoMM: Higher-order moment matching for unsupervised domain adaptation","volume-title":"Proc. AAAI Conf. Artif. Intell. (AAAI)","volume":"34","author":"Chen"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.290"},{"key":"ref131","first-page":"935","article-title":"Improvements in RWTH\u2019s system for off-line handwriting recognition","volume-title":"Proc. 12th Int. Conf. Document Anal. Recognit.","author":"Kozielski"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR.2014.54"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1117\/12.911981"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178341"},{"key":"ref135","article-title":"Deep neural networks for large vocabulary handwritten text recognition","author":"Bluche","year":"2015"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_23"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR-2018.2018.00023"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.40078"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.40077"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00490"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2014.24"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR2020.2020.00013"},{"key":"ref143","first-page":"1","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Frome"},{"key":"ref144","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv:1411.2539"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00590"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"ref155","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref156","first-page":"1","article-title":"Consensus-aware visual-semantic embedding for image-text matching","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Wang"},{"key":"ref157","first-page":"1","article-title":"Adaptive offline quintuplet loss for image-text matching","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Chen"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00791"},{"key":"ref160","first-page":"1","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Akbari"},{"key":"ref161","article-title":"Multimodal self-supervised learning of general audio representations","author":"Wang","year":"2021","journal-title":"arXiv:2104.12807"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref163","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"162","author":"Baevski"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00021"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547867"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548365"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548195"},{"key":"ref169","first-page":"1942","article-title":"Batch renormalization: Towards reducing minibatch dependence in batch-normalized models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ioffe"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10235987.pdf?arnumber=10235987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T23:09:20Z","timestamp":1709334560000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10235987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":169,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3310819","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}