{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T18:48:17Z","timestamp":1781981297035,"version":"3.54.5"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"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":[[2020,10]]},"DOI":"10.1109\/icip40778.2020.9191268","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T20:45:18Z","timestamp":1601498718000},"page":"2556-2560","source":"Crossref","is-referenced-by-count":20,"title":["Cross-Modal Deep Networks For Document Image Classification"],"prefix":"10.1109","author":[{"given":"Souhail","family":"Bakkali","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuheng","family":"Ming","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mickael","family":"Coustaty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcal","family":"Rusinol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.71"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.149"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.217"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/PL00013566"},{"key":"ref15","first-page":"139","article-title":"One-class svms for document classification","volume":"2","author":"manevitz","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/info10040150"},{"key":"ref17","article-title":"Efficient estimation of word representations in vector space","volume":"abs 1301 3781","author":"mikolov","year":"2013","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref19","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume":"abs 1906 8237","author":"yang","year":"2019","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2960811.2960814"},{"key":"ref6","article-title":"Learning transferable architectures for scalable image recognition","volume":"abs 1707 7012","author":"zoph","year":"2017","journal-title":"CoRR"},{"key":"ref5","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"abs 1810 4805","author":"devlin","year":"2018","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00227"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.10.030"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333933"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-006-0020-2"},{"key":"ref9","article-title":"Multimodal deep networks for text and image-based document classification","volume":"abs 1907 6370","author":"audebert","year":"2019","journal-title":"CoRR"},{"key":"ref20","first-page":"2267","article-title":"Recurrent convolutional neural networks for text classification","author":"lai","year":"0","journal-title":"Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence 2015 AAAI’15"},{"key":"ref22","article-title":"Rethinking the inception architecture for computer vision","volume":"abs 1512 567","author":"szegedy","year":"2015","journal-title":"CoRR"},{"key":"ref21","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","volume":"abs 1704 4861","author":"howard","year":"2017","journal-title":"CoRR"},{"key":"ref23","article-title":"Improved regularization of convolutional neural networks with cutout","volume":"abs 1708 4552","author":"devries","year":"2017","journal-title":"CoRR"}],"event":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2020,10,25]]},"end":{"date-parts":[[2020,10,28]]}},"container-title":["2020 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9184803\/9190635\/09191268.pdf?arnumber=9191268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:12:45Z","timestamp":1656375165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9191268\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icip40778.2020.9191268","relation":{},"subject":[],"published":{"date-parts":[[2020,10]]}}}