{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:49:27Z","timestamp":1763059767172,"version":"3.45.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"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":[[2025,9,30]]},"DOI":"10.1109\/sibgrapi67909.2025.11223349","type":"proceedings-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T18:26:15Z","timestamp":1762885575000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Towards Zero-Shot Document Image Classification"],"prefix":"10.1109","author":[{"given":"Lucas","family":"Macedo","sequence":"first","affiliation":[{"name":"University of Brasília,Department of Computer Science,Brasília,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00e3o Paulo","family":"Costa","sequence":"additional","affiliation":[{"name":"University of Brasília,Department of Computer Science,Brasília,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00e3o Pedro Felix","family":"De Almeida","sequence":"additional","affiliation":[{"name":"University of Brasília,Department of Computer Science,Brasília,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro","family":"Freitas","sequence":"additional","affiliation":[{"name":"University of Brasília,Department of Computer Science,Brasília,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Weigang","sequence":"additional","affiliation":[{"name":"University of Brasília,Department of Computer Science,Brasília,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"12","key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-024-11000-0","article-title":"A survey of recent approaches to form understanding in scanned documents","volume":"57","author":"Abdallah","year":"2024","journal-title":"Artificial Intelligence Review"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icdar.2015.7333910"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-021-00378-0"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"2394","DOI":"10.1109\/CVPRW50498.2020.00289","article-title":"Visual and Textual Deep Feature Fusion for Document Image Classification","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Bakkali","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2857768"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event, ser. Proceedings of Machine Learning Research","volume":"139","author":"Radford","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/wacv48630.2021.00225"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539043"},{"key":"ref9","article-title":"CORD: a consolidated receipt dataset for post-ocr parsing","volume-title":"Document Intelligence Workshop at NeurIPS 2019","author":"Park","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icdar.2019.00244"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"ref12","article-title":"Layoutxlm: Multimodal pre-training for multilingual visuallyrich document understanding","volume":"abs\/2104.08836","author":"Xu","year":"2021","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2005.202"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70546-5_8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78495-8_10"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"7499","DOI":"10.18653\/v1\/2023.findings-acl.473","article-title":"Contrastive training improves zero-shot classification of semi-structured documents","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Khalifa","year":"2023"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"2665","DOI":"10.18653\/v1\/2023.eacl-main.195","article-title":"On Evaluation of Document Classification with RVL-CDIP","volume-title":"Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics","author":"Larson","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500845"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00371","volume-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings","author":"Simonyan","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00140"},{"key":"ref23","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019","volume":"97","author":"Tan","year":"2019"},{"key":"ref24","article-title":"An image is worth 16 \\times 16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","author":"Dosovitskiy","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2019.2912815"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86337-1_48"},{"volume-title":"PyTorch: An Imperative Style, HighPerformance Deep Learning Library","year":"2019","author":"Paszke","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"volume-title":"Adam: A method for stochastic optimization","year":"2015","author":"Kingma","key":"ref29"},{"key":"ref30","first-page":"1","article-title":"Super convergence cosine annealing with warm-up learning rate","volume-title":"CAIBDA 2022, 2nd International Conference on Artificial Intelligence, Big Data and Algorithms","author":"Liu","year":"2022"},{"issue":"86","key":"ref31","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","start":{"date-parts":[[2025,9,30]]},"location":"Salvador, Brazil","end":{"date-parts":[[2025,10,3]]}},"container-title":["2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11223285\/11223275\/11223349.pdf?arnumber=11223349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:42:32Z","timestamp":1763059352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/sibgrapi67909.2025.11223349","relation":{},"subject":[],"published":{"date-parts":[[2025,9,30]]}}}