{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:26:03Z","timestamp":1785421563730,"version":"3.56.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["62001289"],"award-info":[{"award-number":["62001289"]}],"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":["61976120"],"award-info":[{"award-number":["61976120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of Key Laboratory of Artificial Intelligence"},{"DOI":"10.13039\/100010449","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010449","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20231337"],"award-info":[{"award-number":["BK20231337"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Key Foundation of Jiangsu Education Department","award":["21KJA510004"],"award-info":[{"award-number":["21KJA510004"]}]},{"name":"Shanghai Super Doctoral Incentive Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tetci.2024.3358184","type":"journal-article","created":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T18:48:38Z","timestamp":1707158918000},"page":"1756-1771","source":"Crossref","is-referenced-by-count":9,"title":["MTCAM: A Novel Weakly-Supervised Audio-Visual Saliency Prediction Model With Multi-Modal Transformer"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6436-7088","authenticated-orcid":false,"given":"Dandan","family":"Zhu","sequence":"first","affiliation":[{"name":"Institute of AI Education, Shanghai, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5773-5089","authenticated-orcid":false,"given":"Kun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Embedded System and Service Computing, Ministry of Education, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3180-7347","authenticated-orcid":false,"given":"Weiping","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Computer and Science and Technology, Nantong University, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6345-7858","authenticated-orcid":false,"given":"Nana","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Donghua University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"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, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00482"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2966082"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3758\/BF03211521"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.26.5.1583"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.16910\/jemr.5.4.2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.16910\/jemr.6.4.1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.34.5.1053"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3251695"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.013"},{"key":"ref12","first-page":"1","article-title":"Simple vs complex temporal recurrences for video saliency prediction","volume-title":"Proc. 30th Brit. Mach. Vis. Conf.","author":"Linardos","year":"2019"},{"key":"ref13","article-title":"Predicting video saliency with object-to-motion CNN and two-layer convolutional LSTM","author":"Jiang","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref16","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.404"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2014.6982312"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3203421"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2934350"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2670143"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3185252"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817538"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2829867"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.12.010"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00248"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.152"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2567391"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.436"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref37","article-title":"SS-CAM: Smoothed score-CAM for sharper visual feature localization","author":"Wang","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089943"},{"key":"ref39","first-page":"983","article-title":"Ablation-CAM: Visual explanations for deep convolutional network via gradient-free localization","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis.","author":"Ramaswamy","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206626"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_37"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00623"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01256"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01487"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00116"},{"key":"ref46","article-title":"SalGAN: Visual saliency prediction with generative adversarial networks","author":"Pan","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.71"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936112"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2966453"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00886"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10480102\/10422835.pdf?arnumber=10422835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T08:45:50Z","timestamp":1725612350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10422835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":50,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3358184","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}