{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T07:40:09Z","timestamp":1737445209117,"version":"3.33.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,6]]},"DOI":"10.1109\/smc54092.2024.10831373","type":"proceedings-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:20Z","timestamp":1737398360000},"page":"3167-3174","source":"Crossref","is-referenced-by-count":0,"title":["RobustLayoutLM: Leveraging Optimized Layout with Additional Modalities for Improved Document Understanding"],"prefix":"10.1109","author":[{"given":"Bowen","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Wei","sequence":"additional","affiliation":[{"name":"Shanghai University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1992.201771"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/34.244677"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/34.584106"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.1995.602059"},{"journal-title":"Hierarchical representation of optically scanned documents","year":"1984","author":"Nagy","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.140"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.247"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.142"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.462"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1476"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1348"},{"journal-title":"vldoc: Bidirectional vision-language modeling for visually-rich document understanding","year":"2022","author":"Luo","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00685"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01373"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.28"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"journal-title":"weight decay regularization","year":"2017","author":"Loshchilov","key":"ref32"},{"key":"ref33","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Kenton","year":"2019"},{"journal-title":"A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref34"}],"event":{"name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2024,10,6]]},"location":"Kuching, Malaysia","end":{"date-parts":[[2024,10,10]]}},"container-title":["2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830919\/10830920\/10831373.pdf?arnumber=10831373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T06:58:18Z","timestamp":1737442698000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10831373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/smc54092.2024.10831373","relation":{},"subject":[],"published":{"date-parts":[[2024,10,6]]}}}