{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:20:09Z","timestamp":1740133209853,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1406703","2020YFB1406704"],"award-info":[{"award-number":["2020YFB1406703","2020YFB1406704"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872256"],"award-info":[{"award-number":["61872256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council (RGC) of the Hong Kong Special Administrative Region, China","doi-asserted-by":"publisher","award":["CityU 11250716"],"award-info":[{"award-number":["CityU 11250716"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3113165","type":"journal-article","created":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T21:00:48Z","timestamp":1632517248000},"page":"8130-8143","source":"Crossref","is-referenced-by-count":4,"title":["Learning to Match Anchor-Target Video Pairs With Dual Attentional Holographic Networks"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0695-1566","authenticated-orcid":false,"given":"Yanbin","family":"Hao","sequence":"first","affiliation":[]},{"given":"Chong-Wah","family":"Ngo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9213-2611","authenticated-orcid":false,"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"2225","article-title":"Aggregated multi-GANs for controlled 3D human motion prediction","volume":"35","author":"liu","year":"2021","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00556"},{"key":"ref33","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578760"},{"article-title":"CMUSMU TRECVID 2015: Video hyperlinking","year":"2015","author":"cheng","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-014-1468-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"},{"key":"ref36","first-page":"1","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"brock","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2737329"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2610324"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578750"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578752"},{"article-title":"TRECVID 2015: An overview of the goals, tasks, data, evaluation mechanisms, and metrics","year":"2015","author":"over","key":"ref2"},{"key":"ref1","first-page":"16","article-title":"The search and hyperlinking task at mediaeval 2014","author":"eskevich","year":"2014","journal-title":"Proc Mediaeval Workshop"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079038"},{"key":"ref22","first-page":"5852","article-title":"Hierarchical attention transfer network for cross-domain sentiment classification","author":"li","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413809"},{"key":"ref24","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413595"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080790"},{"key":"ref25","first-page":"1955","article-title":"Holographic embeddings of knowledge graphs","author":"nickel","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2483977.2483988"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"article-title":"Evaluating search and hyperlinking: An example of the design, test, refine cycle for metric development","year":"2015","author":"racca","key":"ref55"},{"journal-title":"Openimages A public dataset for large-scale multi-label and multi-class image classification","year":"2017","author":"krasin","key":"ref54"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref52","first-page":"4278","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2222902"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742915"},{"key":"ref40","first-page":"2786","article-title":"Siamese recurrent architectures for learning sentence similarity","author":"mueller","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2802558.2814642"},{"key":"ref13","first-page":"1","article-title":"Eurecom-Polito at TRECVID 2017: Hyperlinking task","author":"huet","year":"2017","journal-title":"Proc 21th Int Workshop Video Retr Eval (TRECVID)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2983563.2983567"},{"key":"ref15","first-page":"1","article-title":"Eurecom at TRECVID 2016. The adhoc video search and video hyperlinking tasks","author":"merialdo","year":"2016","journal-title":"Proc 20th Int Workshop Video Retr Eval"},{"article-title":"Vireo TRECVID 2017: Video-to-text, ad-hoc video search and video hyperlinking","year":"2017","author":"anh","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912064"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486549"},{"article-title":"Trecvid 2017: Evaluating ad-hoc and instance video search, events detection, video captioning and hyperlinking","year":"2017","author":"awad","key":"ref4"},{"article-title":"Trecvid 2016: Evaluating video search, video event detection, localization, and hyperlinking","year":"2016","author":"awad","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912029"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2923121"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8229-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2487788.2487967"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240627"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072356"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916757"},{"key":"ref48","first-page":"2042","article-title":"Convolutional neural network architectures for matching natural language sentences","author":"hu","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2902106"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09547825.pdf?arnumber=9547825","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:10Z","timestamp":1652194270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9547825\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3113165","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2021]]}}}