{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T02:38:17Z","timestamp":1769049497652,"version":"3.49.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62271312"],"award-info":[{"award-number":["62271312"]}],"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":["62225112"],"award-info":[{"award-number":["62225112"]}],"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":["62132006"],"award-info":[{"award-number":["62132006"]}],"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":["62401365"],"award-info":[{"award-number":["62401365"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3461956","type":"journal-article","created":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T17:32:41Z","timestamp":1727112761000},"page":"5392-5407","source":"Crossref","is-referenced-by-count":7,"title":["How is Visual Attention Influenced by Text Guidance? Database and Model"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3054-4268","authenticated-orcid":false,"given":"Yinan","family":"Sun","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-4067","authenticated-orcid":false,"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10182000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547955"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/1073858413514136"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20500-2_48"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3337066"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451338"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3304109.3325818"},{"key":"ref9","article-title":"Perceptual video quality assessment: A survey","author":"Min","year":"2024","journal-title":"arXiv:2402.03413"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/OJID.2024.3351089"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3220404"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-46317-4_29"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350990"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3126590"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190831"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290528"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3251695"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547872"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3295375"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229839"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113794"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870832"},{"key":"ref23","article-title":"Adaptive image quality assessment via teaching large multimodal model to compare","author":"Zhu","year":"2024","journal-title":"arXiv:2405.19298"},{"key":"ref24","article-title":"Towards open-ended visual quality comparison","author":"Wu","year":"2024","journal-title":"arXiv:2402.16641"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2966082"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988148"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref29","article-title":"A benchmark of computational models of saliency to predict human fixations","author":"Judd","year":"2012"},{"key":"ref30","article-title":"CAT2000: A large scale fixation dataset for boosting saliency research","author":"Borji","year":"2015","journal-title":"arXiv:1505.03581"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.272"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.26"},{"key":"ref34","first-page":"1","article-title":"Deep Gaze I: Boosting saliency prediction with feature maps trained on imageNet","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"K\u00fcmmerer"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.620"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3050303"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2985531"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947352"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref44","first-page":"155","article-title":"Saliency based on information maximization","volume-title":"Proc. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","volume":"18","author":"Bruce"},{"key":"ref45","first-page":"241","article-title":"Predicting human gaze using low-level saliency combined with face detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"20","author":"Cerf"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1167\/13.4.11"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2009.5204207"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.147"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710620"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00224"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2851672"},{"key":"ref52","article-title":"SalGAN: Visual saliency prediction with generative adversarial networks","author":"Pan","year":"2017","journal-title":"arXiv:1701.01081"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2945857"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2935715"},{"key":"ref55","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref60","volume-title":"Tobii Pro","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2815601"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.147"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1510393112"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.080"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00625"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111279"},{"key":"ref67","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref69","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref70","article-title":"Masked autoencoders as image processors","author":"Duan","year":"2023","journal-title":"arXiv:2303.17316"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3172882"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1167\/8.7.32"},{"key":"ref73","first-page":"681","article-title":"Dynamic visual attention: Searching for coding length increments","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"21","author":"Hou"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10689368.pdf?arnumber=10689368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T17:28:47Z","timestamp":1727976527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10689368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3461956","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}