{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:17:17Z","timestamp":1757456237550,"version":"3.28.0"},"reference-count":28,"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\/icpr56361.2022.9956120","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"1657-1663","source":"Crossref","is-referenced-by-count":4,"title":["Information Extraction from Visually Rich Documents with Font Style Embeddings"],"prefix":"10.1109","author":[{"given":"Ismail","family":"Oussaid","sequence":"first","affiliation":[{"name":"BNP Paribas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Vanhuffel","sequence":"additional","affiliation":[{"name":"BNP Paribas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pirashanth","family":"Ratnamogan","sequence":"additional","affiliation":[{"name":"BNP Paribas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mhamed","family":"Hajaiej","sequence":"additional","affiliation":[{"name":"BNP Paribas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexis","family":"Mathey","sequence":"additional","affiliation":[{"name":"BNP Paribas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Gilles","sequence":"additional","affiliation":[{"name":"BNP Paribas"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","year":"2016","author":"ren","key":"ref10"},{"key":"ref11","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref12","article-title":"Kleister: A novel task for information extraction involving long documents with complex layout","author":"grali?ski","year":"2020","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-2005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1476"},{"article-title":"Visual-WordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach","year":"2020","author":"kerroumi","key":"ref15"},{"article-title":"Attention Is All You Need","year":"2017","author":"vaswani","key":"ref16"},{"key":"ref17","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1206"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12520"},{"key":"ref28","first-page":"1773","article-title":"pdf2table: A method to extract table information from pdf files","volume":"2005","author":"yildiz","year":"0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00294"},{"key":"ref3","article-title":"OntoNotes Release 5.0 LDC2013T19","author":"weischedel","year":"2013","journal-title":"Linguistic Data Consortium"},{"key":"ref6","article-title":"CORD: A Consolidated Receipt Dataset for Post-OCR Parsing","author":"park","year":"2019","journal-title":"Workshop on Document Intelligence at NeurIPS 2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"article-title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","year":"2020","author":"xu","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/5.156468"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119195"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86331-9_47"},{"key":"ref1","article-title":"Layout LM: Pre-training of text and layout for document image understanding","author":"xu","year":"2019","journal-title":"Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining-KDD"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1206"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874254"},{"article-title":"HuggingFace's Transformers: State-of-the-art natural language processing","year":"2019","author":"debut","key":"ref23"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1109\/ICDAR.2007.4376991","article-title":"An overview of the Tesseract OCR engine","volume":"2","author":"smith","year":"2007","journal-title":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)"},{"key":"ref25","first-page":"82","article-title":"Text Chunking using Transformation-Based Learning","author":"ramshaw","year":"1995","journal-title":"third workshop on very large corpora"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","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\/09956120.pdf?arnumber=9956120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:04:15Z","timestamp":1671480255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956120","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}