{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T15:09:52Z","timestamp":1780153792525,"version":"3.54.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Guangdong International Technology Cooperation Project","award":["2022A0505050009"],"award-info":[{"award-number":["2022A0505050009"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province, China","award":["2020B010165004"],"award-info":[{"award-number":["2020B010165004"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province, China","award":["2020B010166003"],"award-info":[{"award-number":["2020B010166003"]}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council of the Hong Kong Special Administrative Region, China","doi-asserted-by":"publisher","award":["UGC\/FDS11\/E01\/21"],"award-info":[{"award-number":["UGC\/FDS11\/E01\/21"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3270105","type":"journal-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T18:30:56Z","timestamp":1682706656000},"page":"2636-2648","source":"Crossref","is-referenced-by-count":6,"title":["Panel-Page-Aware Comic Genre Understanding"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0377-8646","authenticated-orcid":false,"given":"Chenshu","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8006-3663","authenticated-orcid":false,"given":"Xuemiao","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nanxuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0665-1993","authenticated-orcid":false,"given":"Weiwei","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7662-9831","authenticated-orcid":false,"given":"Huaidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Future Technology, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1519-750X","authenticated-orcid":false,"given":"Chengze","family":"Li","sequence":"additional","affiliation":[{"name":"Caritas Institute of Higher Education, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0868-5353","authenticated-orcid":false,"given":"Xueting","family":"Liu","sequence":"additional","affiliation":[{"name":"Caritas Institute of Higher Education, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6909"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref53","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_10"},{"key":"ref16","article-title":"Asymmetric loss for multi-label classification","author":"ben-baruch","year":"2020","journal-title":"arXiv 2009 14119"},{"key":"ref19","article-title":"Judging a book by its cover","author":"iwana","year":"2016","journal-title":"arXiv 1610 09204"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref50","year":"2022","journal-title":"Manga Image Translator"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref45","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2100463"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref43","year":"2022","journal-title":"Kumiko the Comics Cutter"},{"key":"ref49","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","author":"kim","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref6","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"arXiv 1406 2199"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref40","article-title":"Aggregating nested transformers","author":"zhang","year":"2021","journal-title":"arXiv 2105 12723"},{"key":"ref35","article-title":"Symbiotic attention for egocentric action recognition with object-centric alignment","author":"wang","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3191461"},{"key":"ref37","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref36","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2778563"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref33","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"2021","journal-title":"arXiv 2102 05095"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2018.73"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","article-title":"Scaling vision transformers","author":"zhai","year":"2021","journal-title":"arXiv 2106 04560"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-021-1248-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00035"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3132515.3132516"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201355"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2831447"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10112648.pdf?arnumber=10112648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:48:33Z","timestamp":1685382513000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10112648\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3270105","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}