{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:45:36Z","timestamp":1781279136591,"version":"3.54.1"},"reference-count":62,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3372469","type":"journal-article","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T19:28:27Z","timestamp":1709839707000},"page":"1911-1922","source":"Crossref","is-referenced-by-count":8,"title":["Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9124-2600","authenticated-orcid":false,"given":"Tingtian","family":"Li","sequence":"first","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixun","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Xiao","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.114"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.526"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-75786-5_3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_16"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00785"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16354"},{"key":"ref16","first-page":"24206","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Akbari"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462993"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2636739"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713099"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3031184"},{"key":"ref25","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref27","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Baevski"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00958"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2011.6012139"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394263"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521352"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12335"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_18"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463597"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019143"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298981"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_12"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247852"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.538"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"ref45","first-page":"2069","article-title":"Diverse sequential subset selection for supervised video summarization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Gong"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.395"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.455"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref50","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015","journal-title":"arXiv:1511.06434"},{"key":"ref51","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683786"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007327622663"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2139"},{"key":"ref55","article-title":"Trace norm regularised deep multi-task learning","author":"Yang","year":"2016","journal-title":"arXiv:1606.04038"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01365"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10462646.pdf?arnumber=10462646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T11:33:11Z","timestamp":1711452791000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10462646\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3372469","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}