{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:05:26Z","timestamp":1777568726239,"version":"3.51.4"},"reference-count":110,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276016"],"award-info":[{"award-number":["62276016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372029"],"award-info":[{"award-number":["62372029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3458921","type":"journal-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T17:50:58Z","timestamp":1726077058000},"page":"11152-11167","source":"Crossref","is-referenced-by-count":17,"title":["Learning From Human Attention for Attribute-Assisted Visual Recognition"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8561-9299","authenticated-orcid":false,"given":"Xiao","family":"Bai","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, State Key Laboratory of Complex & Critical Software Environment, Jiangxi Research Institute, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8585-7545","authenticated-orcid":false,"given":"Pengcheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, State Key Laboratory of Complex & Critical Software Environment, Jiangxi Research Institute, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6186-0520","authenticated-orcid":false,"given":"Xiaohan","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5218-9250","authenticated-orcid":false,"given":"Jin","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, State Key Laboratory of Complex & Critical Software Environment, Jiangxi Research Institute, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4496-2028","authenticated-orcid":false,"given":"Edwin R.","family":"Hancock","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of York, York, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5822-8233","authenticated-orcid":false,"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Southport, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7419-6240","authenticated-orcid":false,"given":"Lin","family":"Gu","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00961"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_33"},{"key":"ref7","article-title":"See better before looking closer: Weakly supervised data augmentation network for fine-grained visual classification","author":"Hu","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"ref9","first-page":"14943","article-title":"Semantic-guided multi-attention localization for zero-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00311"},{"key":"ref11","first-page":"21969","article-title":"Attribute prototype network for zero-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2921876"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055617"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.679"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref19","article-title":"A simple yet effective network based on vision transformer for camouflaged object and salient object detection","author":"Hao","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00379"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.001"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00875"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.04.095"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11197"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_46"},{"key":"ref27","article-title":"Leveraging human selective attention for medical image analysis with limited training data","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Huang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3146973"},{"key":"ref29","article-title":"Human attention in fine-grained classification","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Rong"},{"key":"ref30","first-page":"12992","article-title":"Glance-and-gaze vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.71"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007841"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.111"},{"key":"ref40","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Frome"},{"key":"ref41","first-page":"2152","article-title":"An embarrassingly simple approach to zero-shot learning","author":"Romera-Paredes","year":"2015","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.15"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.321"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.220"},{"key":"ref47","first-page":"2005","article-title":"Generalized zero-shot learning with deep calibration network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00113"},{"key":"ref49","first-page":"5995","article-title":"Stacked semantics-guided attention model for fine-grained zero-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ji"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_4"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00436"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2973812"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01483"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00066"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.128"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108067"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108691"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.47"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.132"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298685"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01418-6_38"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref76","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref81","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref83","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19991119"},{"key":"ref85","first-page":"7603","article-title":"Preserving semantic relations for zero-shot learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Annadani"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00115"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01043"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00986"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01405"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00454"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_2"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00844"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01331"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01288"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_36"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_5"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00779"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00680"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01268"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"ref103","first-page":"2251","author":"Xian","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3229526"},{"key":"ref105","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00368"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.118"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2005.03.019"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3249481"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10678838.pdf?arnumber=10678838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:38:08Z","timestamp":1732667888000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10678838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":110,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3458921","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}