{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T03:33:41Z","timestamp":1770348821296,"version":"3.49.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF) Grant funded by the Korea Government","doi-asserted-by":"publisher","award":["NRF-2020R1G1A1100674"],"award-info":[{"award-number":["NRF-2020R1G1A1100674"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3209810","type":"journal-article","created":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T20:39:19Z","timestamp":1664224759000},"page":"102968-102980","source":"Crossref","is-referenced-by-count":7,"title":["Convolved Quality Transformer: Image Quality Assessment via Long-Range Interaction Between Local Perception"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0920-7281","authenticated-orcid":false,"given":"Heeseok","family":"Oh","sequence":"first","affiliation":[{"name":"Department of Applied AI, Hansung University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1437-2206","authenticated-orcid":false,"given":"Jinwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3319-7797","authenticated-orcid":false,"given":"Taewan","family":"Kim","sequence":"additional","affiliation":[{"name":"Data Science Major, Dongduk Women’s University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9895-5347","authenticated-orcid":false,"given":"Sanghoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.864165"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2639328"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745362"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2014.7051495"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2109730"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2346028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298853"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.01.054"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3040656"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2736018"},{"key":"ref16","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref17","article-title":"SeMask: Semantically masked transformers for semantic segmentation","author":"Jain","year":"2021","journal-title":"arXiv:2112.12782"},{"key":"ref18","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv:2203.03605"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00054"},{"key":"ref20","article-title":"Transformer for image quality assessment","author":"You","year":"2020","journal-title":"arXiv:2101.01097"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00196"},{"key":"ref22","article-title":"VTAMIQ: Transformers for attention modulated image quality assessment","author":"Chubarau","year":"2021","journal-title":"arXiv:2110.01655"},{"key":"ref23","article-title":"Multi-scale features and parallel transformers based image quality assessment","author":"Keshari","year":"2022","journal-title":"arXiv:2204.09779"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2725584"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09825-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1117\/1.3267105"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2014.10.009"},{"key":"ref31","first-page":"30","article-title":"TID2008\u2014A database for evaluation of full-reference visual quality assessment metrics","volume":"10","author":"Ponomarenko","year":"2009","journal-title":"Adv. Modern Radioelectronics"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2016.16.HVEI-103"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2293423"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2760518"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.213"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00194"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00222"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref41","article-title":"CSWin transformer: A general vision transformer backbone with cross-shaped Windows","author":"Dong","year":"2021","journal-title":"arXiv:2107.00652"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref43","article-title":"Escaping the big data paradigm with compact transformers","author":"Hassani","year":"2021","journal-title":"arXiv:2104.05704"},{"key":"ref44","article-title":"Early convolutions help transformers see better","author":"Xiao","year":"2021","journal-title":"arXiv:2106.14881"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref48","article-title":"CMT: Convolutional neural networks meet vision transformers","author":"Guo","year":"2021","journal-title":"arXiv:2107.06263"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00123"},{"key":"ref51","first-page":"63","article-title":"ESRGAN: Enhanced super-resolution generative adversarial networks","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP)","author":"Wang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_47"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref54","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","author":"Dai","year":"2021","journal-title":"arXiv:2106.04803"},{"key":"ref55","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2009.2015374"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.1896.0007"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.2307\/1412159"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref64","first-page":"2579","article-title":"Visualizaing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11045-017-0475-y"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09903435.pdf?arnumber=9903435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:25:38Z","timestamp":1705962338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9903435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3209810","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}