{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T14:08:06Z","timestamp":1782828486724,"version":"3.54.5"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973245"],"award-info":[{"award-number":["61973245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Plan of Shaanxi Province","award":["2023-YBGY-029"],"award-info":[{"award-number":["2023-YBGY-029"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tcsvt.2023.3287296","type":"journal-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:23:28Z","timestamp":1687199008000},"page":"504-517","source":"Crossref","is-referenced-by-count":7,"title":["DCMAI: A Dynamical Cross-Modal Alignment Interaction Framework for Document Key Information Extraction"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5939-007X","authenticated-orcid":false,"given":"Pengcheng","family":"Guo","sequence":"first","affiliation":[{"name":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5978-3781","authenticated-orcid":false,"given":"Yonghong","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongbiao","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang-Kang","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingjie","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haijun","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BERTgrid: Contextualized embedding for 2D document representation and understanding","author":"Denk","year":"2019","journal-title":"arXiv:1909.04948"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86159-9_28"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"ref4","article-title":"GraphIE: A graph-based framework for information extraction","author":"Qian","year":"2018","journal-title":"arXiv:1810.13083"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/144"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref7","article-title":"LayoutLMv2: Multi-modal pre-training for visually-rich document understanding","author":"Xu","year":"2020","journal-title":"arXiv:2012.14740"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref13","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref15","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1476"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413900"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/384"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"ref21","first-page":"816","article-title":"Learning equivariant segmentation with instance-unique querying","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref25","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Gutmann"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref27","first-page":"1","article-title":"Improving language understanding with unsupervised learning","volume":"17","author":"Alec","year":"2018","journal-title":"Citado"},{"key":"ref28","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3182549"},{"key":"ref30","first-page":"39","article-title":"Unidoc: Unified pretraining framework for document understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Gu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164230"},{"key":"ref32","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3105143"},{"key":"ref34","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref35","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063423"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512032"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.80"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475345"},{"key":"ref41","first-page":"747","article-title":"MixPAVE: Mix-prompt tuning for few-shot product attribute value extraction","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics (Long Papers)","volume":"1","author":"Wang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.135"},{"key":"ref43","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref44","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cho"},{"key":"ref47","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","volume-title":"Proc. ICML","author":"Nair"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.274"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3186714"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148307"},{"key":"ref53","first-page":"1","article-title":"CORD: A consolidated receipt dataset for post-OCR parsing","volume-title":"Proc. Workshop Document Intell. NeurIPS","author":"Park"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_36"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref58","first-page":"642","article-title":"UniLMv2: Pseudo-masked language models for unified language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bao"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref62","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"issue":"11","key":"ref63","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10382161\/10155234.pdf?arnumber=10155234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T10:52:47Z","timestamp":1709290367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10155234\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":63,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3287296","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}