{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:52:25Z","timestamp":1784303545213,"version":"3.55.0"},"reference-count":106,"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":["62002177"],"award-info":[{"award-number":["62002177"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin City","doi-asserted-by":"publisher","award":["21JCYBJC00110"],"award-info":[{"award-number":["21JCYBJC00110"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin City","doi-asserted-by":"publisher","award":["19JCQNJC00300"],"award-info":[{"award-number":["19JCQNJC00300"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3275308","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T17:36:04Z","timestamp":1683826564000},"page":"1011-1026","source":"Crossref","is-referenced-by-count":66,"title":["Transformer Fusion and Pixel-Level Contrastive Learning for RGB-D Salient Object Detection"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6941-3300","authenticated-orcid":false,"given":"Jiesheng","family":"Wu","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangwei","family":"Hao","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7687-5511","authenticated-orcid":false,"given":"Weiyun","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8532-2241","authenticated-orcid":false,"given":"Jing","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.271"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.360"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051099"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2280096"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2202676"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778820"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206573"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301391"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2682981"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206370"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00322"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00405"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996406"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3073689"},{"key":"ref16","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3127149"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475601"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00468"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-020-0199-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2711277"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049959"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2891104"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2761775"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3216198"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref33","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref34","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla","year":"2020"},{"issue":"11","key":"ref35","article-title":"Visualizing data using t-SNE","volume":"9","author":"V. d. Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_23"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00887"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5244\/C.27.98"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2557347"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062689"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2969255"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20257"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3139232"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548037"},{"key":"ref45","article-title":"Promoting saliency from depth: Deep unsupervised RGB-D saliency detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ji","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140606"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3202765"},{"key":"ref52","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref54","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref58","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref60","article-title":"Supervised contrastive learning for pre-trained language model fine-tuning","author":"Gunel","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","article-title":"How much position information do convolutional neural networks encode?","author":"Islam","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00227"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196847"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00146"},{"key":"ref66","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475240"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_31"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_17"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3144852"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/186"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_15"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_41"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025222"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247708"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00735"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.359"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_7"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2632856.2632866"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_39"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_21"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00353"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_4"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00935"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/97"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487833"},{"key":"ref89","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00908"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060167"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00464"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16191"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187856"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_36"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref99","article-title":"CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers","author":"Liu","year":"2022"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3087412"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077058"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102268"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3216476"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924578"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171688"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-1702-6_36"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10122979.pdf?arnumber=10122979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:52:37Z","timestamp":1705690357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10122979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":106,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3275308","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}