{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T04:13:52Z","timestamp":1742703232656,"version":"3.40.2"},"reference-count":41,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2020,1,20]],"date-time":"2020-01-20T00:00:00Z","timestamp":1579478400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61703046"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Computer Vision"],"published-print":{"date-parts":[[2020,2]]},"abstract":"Here, the authors focus on incrementally acquiring heterogeneous knowledge from both internet and publicly available datasets to reduce the tedious and expensive labelling efforts required in video annotation. An incremental transfer learning framework is presented to integrate heterogeneous source knowledge and update the annotation model incrementally during the transfer learning process. Under this framework, web images and existing action videos form the source domain to provide labelled static and motion information of the target domain videos, respectively. Moreover, according to the semantic of the source domain data, all the source domain data are partitioned into several groups. Different from traditional methods, which compare the entire target domain videos with each source group from the source domain, the authors treat the group weights as sample\u2010specific variables and optimise them along with new adding data. Two regularisers are used to prevent the incremental learning process from negative transfer. Experimental results on the two large\u2010scale consumer video datasets (i.e. multimedia event detection (MED) and Columbia consumer video (CCV)) show the effectiveness of the proposed method.<\/jats:p>","DOI":"10.1049\/iet-cvi.2018.5730","type":"journal-article","created":{"date-parts":[[2019,11,19]],"date-time":"2019-11-19T02:26:29Z","timestamp":1574130389000},"page":"26-35","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Incremental transfer learning for video annotation via grouped heterogeneous sources"],"prefix":"10.1049","volume":"14","author":[{"given":"Han","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Visual Media, School of Information and Technology Beijing Forestry University People's Republic of China"}]},{"given":"Hao","family":"Song","sequence":"additional","affiliation":[{"name":"Beijing Lab of Intelligent Information Technology and the School of Computer Science Beijing Institute of Technology People's Republic of China"}]},{"given":"Xinxiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Lab of Intelligent Information Technology and the School of Computer Science Beijing Institute of Technology People's Republic of China"}]},{"given":"Yunde","family":"Jia","sequence":"additional","affiliation":[{"name":"Beijing Lab of Intelligent Information Technology and the School of Computer Science Beijing Institute of Technology People's Republic of China"}]}],"member":"265","published-online":{"date-parts":[[2020,1,20]]},"reference":[{"key":"e_1_2_8_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11792"},{"key":"e_1_2_8_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.106"},{"volume-title":"European Conf. Computer Vision","year":"2015","author":"Gan C.","key":"e_1_2_8_4_2"},{"key":"e_1_2_8_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806226"},{"key":"e_1_2_8_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.518"},{"key":"e_1_2_8_7_2","first-page":"1959","volume-title":"IEEE Conf. on Computer Vision and Pattern Recognition","author":"Duan L.","year":"2012"},{"key":"e_1_2_8_8_2","first-page":"1395","volume-title":"Tenth IEEE Int. Conf. on Computer Vision","author":"Blank M.","year":"2005"},{"key":"e_1_2_8_9_2","first-page":"32","volume-title":"Proc. of the 17th Int. Conf. on Pattern Recognition","author":"Schmid C.","year":"2004"},{"key":"e_1_2_8_10_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/158"},{"key":"e_1_2_8_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126344"},{"key":"e_1_2_8_12_2","first-page":"7948","volume-title":"IEEE Conf. on Computer Vision and Pattern Recognition","author":"Lv J.","year":"2018"},{"key":"e_1_2_8_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291276"},{"key":"e_1_2_8_14_2","first-page":"1375","volume-title":"IEEE Conf. on Computer Vision and Pattern Recognition","author":"Duan L.","year":"2009"},{"key":"e_1_2_8_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539870"},{"key":"e_1_2_8_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0717-5"},{"key":"e_1_2_8_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654913"},{"key":"e_1_2_8_18_2","unstructured":"Wen L. Limin W. Wei L. et al: \u2018Webvision database: visual learning and understanding from web data\u2019 arXiv:1708.02862 2017"},{"key":"e_1_2_8_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00571"},{"volume-title":"IEEE Conf. on Computer Vision and Pattern Recognition","year":"2010","author":"Doretto G.","key":"e_1_2_8_20_2"},{"volume-title":"Advances in Neural Information Processing Systems","year":"2009","author":"Schweikert G.","key":"e_1_2_8_21_2"},{"key":"e_1_2_8_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350955"},{"key":"e_1_2_8_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2306419"},{"key":"e_1_2_8_24_2","first-page":"647","volume-title":"Advances in Neural Information Processing Systems","author":"Tang K.","year":"2012"},{"key":"e_1_2_8_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.344"},{"key":"e_1_2_8_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2312251"},{"key":"e_1_2_8_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.431"},{"key":"e_1_2_8_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/1899412.1899414"},{"key":"e_1_2_8_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-010-0599-7"},{"key":"e_1_2_8_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553408"},{"key":"e_1_2_8_31_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl242"},{"volume-title":"Advances in Neural Information Processing Systems","year":"2008","author":"Gretton A.","key":"e_1_2_8_32_2"},{"key":"e_1_2_8_33_2","first-page":"1517","article-title":"Hilbert space embeddings and metrics on probability measures","volume":"99","author":"Sriperumbudur B.K.","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_2_8_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"e_1_2_8_35_2","unstructured":"\u2018Med2014\u2019. Available at:http:\/\/www.nist.gov\/itl\/iad\/mig\/med14.cfm"},{"key":"e_1_2_8_36_2","first-page":"675","article-title":"Caffe: convolutional architecture for fast feature embedding","author":"Jia Y.","year":"2014","journal-title":"Eprint Arxiv"},{"key":"e_1_2_8_37_2","first-page":"2012","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky A.","year":"2012","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"e_1_2_8_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.57"},{"key":"e_1_2_8_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2011.2178556"},{"key":"e_1_2_8_40_2","first-page":"409","volume-title":"Advances in Neural Information Processing Systems: Proc. of the 2000 Conf.","author":"Poggio G.C.","year":"2001"},{"volume-title":"Int. Conf. on Machine Learning (ICML)","year":"2015","author":"Long M.","key":"e_1_2_8_41_2"},{"volume-title":"Asian Conf. Machine Learning","year":"2018","author":"Shen C.","key":"e_1_2_8_42_2"}],"container-title":["IET Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/iet-cvi.2018.5730","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/iet-cvi.2018.5730","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/iet-cvi.2018.5730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T10:59:47Z","timestamp":1742641187000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/iet-cvi.2018.5730"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,20]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,2]]}},"alternative-id":["10.1049\/iet-cvi.2018.5730"],"URL":"https:\/\/doi.org\/10.1049\/iet-cvi.2018.5730","archive":["Portico"],"relation":{},"ISSN":["1751-9632","1751-9640"],"issn-type":[{"type":"print","value":"1751-9632"},{"type":"electronic","value":"1751-9640"}],"subject":[],"published":{"date-parts":[[2020,1,20]]},"assertion":[{"value":"2018-11-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-11-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-01-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}