{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T21:51:32Z","timestamp":1757454692680,"version":"3.44.0"},"reference-count":109,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP190102443"],"award-info":[{"award-number":["DP190102443"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-19-1-0356"],"award-info":[{"award-number":["W911NF-19-1-0356"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015539","name":"Australian Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015539","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Office of National Intelligence National Intelligence Postdoctoral","award":["NIPG-2021-001"],"award-info":[{"award-number":["NIPG-2021-001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/tai.2021.3134190","type":"journal-article","created":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T16:14:55Z","timestamp":1639066495000},"page":"763-777","source":"Crossref","is-referenced-by-count":11,"title":["Cross-Domain Modality Fusion for Dense Video Captioning"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2763-2094","authenticated-orcid":false,"given":"Nayyer","family":"Aafaq","sequence":"first","affiliation":[{"name":"University of Western Australia, Crawley, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5206-3842","authenticated-orcid":false,"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[{"name":"University of Western Australia, Crawley, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Western Australia, Crawley, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3406-673X","authenticated-orcid":false,"given":"Naveed","family":"Akhtar","sequence":"additional","affiliation":[{"name":"University of Western Australia, Crawley, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8216-1128","authenticated-orcid":false,"given":"Mubarak","family":"Shah","sequence":"additional","affiliation":[{"name":"University of Central Florida, Orlando, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref3","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref5","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref6","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3068697"},{"key":"ref8","first-page":"1533","article-title":"Semantic parsing on freebase from question-answer pairs","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Berant","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref10","first-page":"926","article-title":"Reasoning with neural tensor networks for knowledge base completion","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst","author":"Socher","year":"2013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref14","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3355390"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00313"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICALT.2017.11"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-3112-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2985868"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11297"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601493"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2320814"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_41"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3066565"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916757"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894139"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2020.100052"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928144"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855406"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.780"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2019.00011"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.06.041"},{"key":"ref49","article-title":"Efficient estimation of word representations in vector space","volume-title":"1st Int. Conf. Learning Representations","author":"Mikolov","year":"2013"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459279"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00706"},{"key":"ref55","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Simonyan","year":"2014"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298735"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref62","article-title":"Temporal activity detection in untrimmed videos with recurrent neural networks","volume-title":"Proc. 1st NIPS Workshop Large Scale Comput. Vis. Syst.","author":"Montes","year":"2016"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref69","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Karpathy","year":"2014"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"issue":"2","key":"ref72","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1023\/A:1020346032608","article-title":"Natural language description of human activities from video images based on concept hierarchy of actions","volume":"50","author":"Kojima","year":"2002","journal-title":"Int. J. Comput. Vis."},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1117"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12330"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"ref93","first-page":"3059","article-title":"Weakly supervised dense event captioning in videos","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Duan","year":"2018"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00900"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1049"},{"key":"ref97","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Yang","year":"2019"},{"key":"ref98","first-page":"3294","article-title":"Skip-thought vectors","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Kiros","year":"2015"},{"key":"ref99","article-title":"BERTscore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang","year":"2020"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"volume-title":"Discrete-Time Signal Processing","year":"1999","author":"Oppenheim","key":"ref101"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.198"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_26"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273556"},{"key":"ref108","first-page":"13","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma","year":"2015"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/9924246\/09645262.pdf?arnumber=9645262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:10:03Z","timestamp":1755911403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9645262\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":109,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tai.2021.3134190","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}