{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T10:45:28Z","timestamp":1768992328084,"version":"3.49.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956301","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"1756-1762","source":"Crossref","is-referenced-by-count":11,"title":["Multimodal Tree Decoder for Table of Contents Extraction in Document Images"],"prefix":"10.1109","author":[{"given":"Pengfei","family":"Hu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenrong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianshu","family":"Zhang","sequence":"additional","affiliation":[{"name":"iFLYTEK Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajia","family":"Wu","sequence":"additional","affiliation":[{"name":"iFLYTEK Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Computer Science"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2015.08.004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1117\/12.587293"},{"key":"ref11","article-title":"The national library of medicine","author":"thoma","year":"2005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333898"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.229"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.271"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"ref16","first-page":"13","article-title":"The financial document structure extraction shared task (fintoc 2020)","author":"bentabet","year":"2020","journal-title":"Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1099"},{"key":"ref28","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-010-0127-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333927"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84628-726-8_2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.06.017"},{"key":"ref8","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref2","first-page":"242","article-title":"Enhancing table of contents extraction by system aggregation","volume":"1","author":"doucet","year":"2017","journal-title":"2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) ICDAR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/00014788.2019.1609346"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_35"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.389"},{"key":"ref21","article-title":"Fcos: Fully convolutional one-stage object detection","author":"tian","year":"2020","journal-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"ref24","article-title":"Gated multimodal units for information fusion","author":"arevalo","year":"2017"},{"key":"ref23","article-title":"Split, embed and merge: An accurate table structure recognizer","author":"zhang","year":"2021"},{"key":"ref26","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956301.pdf?arnumber=9956301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:07:13Z","timestamp":1671480433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956301","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}