{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T11:12:48Z","timestamp":1782817968651,"version":"3.54.5"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0116500"],"award-info":[{"award-number":["2022ZD0116500"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206284"],"award-info":[{"award-number":["62206284"]}],"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":["62020106015"],"award-info":[{"award-number":["62020106015"]}],"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":["61976209"],"award-info":[{"award-number":["61976209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDB32040000"],"award-info":[{"award-number":["XDB32040000"]}]},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1109\/tpami.2023.3263181","type":"journal-article","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T17:28:32Z","timestamp":1680197312000},"page":"10760-10777","source":"Crossref","is-referenced-by-count":128,"title":["Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0084-433X","authenticated-orcid":false,"given":"Changde","family":"Du","sequence":"first","affiliation":[{"name":"Research Center for Brain-Inspired Intelligence, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaicheng","family":"Fu","sequence":"additional","affiliation":[{"name":"Research Center for Brain-Inspired Intelligence, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8701-2642","authenticated-orcid":false,"given":"Jinpeng","family":"Li","sequence":"additional","affiliation":[{"name":"Ningbo HwaMei Hospital, UCAS, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-1711","authenticated-orcid":false,"given":"Huiguang","family":"He","sequence":"additional","affiliation":[{"name":"Research Center for Brain-Inspired Intelligence, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc Annu Int Conf Mach Learn"},{"key":"ref57","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics - Hum Lang Technol"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2021.07.006"},{"key":"ref56","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.08.017"},{"key":"ref59","first-page":"1","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"lan","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30761-2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1050"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref52","first-page":"5171","article-title":"On variational bounds of mutual information","author":"poole","year":"2019","journal-title":"Proc Annu Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.4324\/9781315798868"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2105646118"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.08.005"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1111\/j.1551-6709.2010.01106.x"},{"key":"ref17","first-page":"38","article-title":"Large-scale zero-shot image classification from rich and diverse textual descriptions","author":"bujwid","year":"2021","journal-title":"Proc Workshop Beyond Vis Lang Integrating Real-World Knowl"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.06.042"},{"key":"ref19","first-page":"1","article-title":"Generalized multimodal ELBO","author":"sutter","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.250"},{"key":"ref51","first-page":"1779","article-title":"CLUB: A contrastive log-ratio upper bound of mutual information","author":"cheng","year":"2020","journal-title":"Proc Annu Int Conf Mach Learn"},{"key":"ref50","first-page":"531","article-title":"Mutual information neural estimation","author":"belghazi","year":"2018","journal-title":"Proc Annu Int Conf Mach Learn"},{"key":"ref46","first-page":"1","article-title":"Deep variational information bottleneck","author":"alemi","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S19-1013"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref47","first-page":"1","article-title":"Learning representations by maximizing mutual information across views","author":"bachman","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1032"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01052"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1113"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00043"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909031"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1167\/19.10.209a"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature06713"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3028167"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.1152876"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2995909"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms15037"},{"key":"ref5","first-page":"1","article-title":"Zero-shot learning with semantic output codes","author":"palatucci","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref82","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref81","article-title":"Brain hierarchy score: Which deep neural networks are hierarchically brain-like?","volume":"24","author":"nonaka","year":"2021","journal-title":"Science"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.474"},{"key":"ref84","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref83","article-title":"Visual ChatGPT: Talking, drawing and editing with visual foundation models","author":"wu","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.03.010"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00844"},{"key":"ref79","first-page":"2579","article-title":"Visualizing data using t-SNE.","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.15"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-021-00921-6"},{"key":"ref37","first-page":"2152","article-title":"An embarrassingly simple approach to zero-shot learning","author":"romera-paredes","year":"2015","journal-title":"Proc Annu Int Conf Mach Learn"},{"key":"ref36","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-08848-0"},{"key":"ref75","first-page":"1","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"li","year":"2022","journal-title":"Proc Annu Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-03068-4"},{"key":"ref74","first-page":"1","article-title":"Brain-like object recognition with high-performing shallow recurrent ANNs","author":"kubilius","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2012.01.010"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.386"},{"key":"ref76","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2882456"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nn1444"},{"key":"ref39","first-page":"7434","article-title":"Co-representation network for generalized zero-shot learning","author":"zhang","year":"2019","journal-title":"Proc Annu Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00450"},{"key":"ref71","first-page":"2732","article-title":"Variational inference via ? upper bound minimization","author":"dieng","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref70","first-page":"1","article-title":"InfoGan: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0223792"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2015.00023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.22087"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2009.11.064"},{"key":"ref67","first-page":"159","article-title":"Fixing a broken ELBO","author":"alemi","year":"2018","journal-title":"Proc Annu Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.479"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00384"},{"key":"ref69","first-page":"1","article-title":"Variational lossy autoencoder","author":"chen","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006633"},{"key":"ref64","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"2014","journal-title":"Proc Annu Int Conf Mach Learn"},{"key":"ref63","first-page":"1","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.1063736"},{"key":"ref66","first-page":"15692","article-title":"Variational mixture-of-experts autoencoders for multi-modal deep generative models","author":"shi","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119754"},{"key":"ref65","first-page":"5580","article-title":"Multimodal generative models for scalable weakly-supervised learning","author":"wu","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3028701"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.11.003"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nature17637"},{"key":"ref60","article-title":"GPT-Neo: Large scale autoregressive language modeling with mesh-tensorflow","author":"black","year":"2021"},{"key":"ref62","first-page":"201","article-title":"The IM algorithm: A variational approach to information maximization","volume":"16","author":"agakov","year":"2004","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.235"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10210213\/10089190.pdf?arnumber=10089190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T17:55:16Z","timestamp":1693245316000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10089190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":84,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3263181","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":[[2023,9,1]]}}}