{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T18:45:29Z","timestamp":1791485129541,"version":"4.3.4"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Zhejiang NSF","award":["LR21F020004"],"award-info":[{"award-number":["LR21F020004"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272411"],"award-info":[{"award-number":["62272411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies"},{"DOI":"10.13039\/501100012455","name":"China Knowledge Centre for Engineering Sciences and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012455","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3228696","type":"journal-article","created":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:21:57Z","timestamp":1670872917000},"page":"7814-7824","source":"Crossref","is-referenced-by-count":5,"title":["Cross-Modal Data Augmentation for Tasks of Different Modalities"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4859-1757","authenticated-orcid":false,"given":"Dong","family":"Chen","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3540-7997","authenticated-orcid":false,"given":"Zijin","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9145-4531","authenticated-orcid":false,"given":"Carl","family":"Yang","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3131-6916","authenticated-orcid":false,"given":"Guoming","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-9711","authenticated-orcid":false,"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00492-0"},{"key":"ref3","article-title":"Modals: Modality-agnostic automated data augmentation in the latent space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cheung","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545506"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-6101"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.645"},{"key":"ref7","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3046884"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939812"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2645565"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2705068"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref15","first-page":"3846","article-title":"Cross-media shared representation by hierarchical learning with multiple deep networks.","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Peng","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref17","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andrew","year":"2013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2168752.2168767"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8464"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref21","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2022.3225327"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00638"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3069562"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2742704"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3140656"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3142448"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3132166"},{"key":"ref34","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma","year":"2019"},{"key":"ref35","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Huang","year":"2021"},{"key":"ref36","first-page":"28","article-title":"Learning from multiple partially observed views-an application to multilingual text categorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"22","author":"Amini","year":"2009"},{"key":"ref37","first-page":"7852","article-title":"On the theory of transfer learning: The importance of task diversity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Tripuraneni","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/79.543975"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00536"},{"key":"ref42","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref43","article-title":"bert-as-service","author":"Xiao","year":"2018"},{"key":"ref44","article-title":"SSD: A unified framework for self-supervised outlier detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sehwag","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-1609"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00250"},{"key":"ref48","article-title":"You only cut once: Boosting data augmentation with a single cut","author":"Han","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref52","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2015"},{"key":"ref53","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":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09982421.pdf?arnumber=9982421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T22:24:48Z","timestamp":1703024688000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9982421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3228696","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}