{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T15:05:44Z","timestamp":1771599944736,"version":"3.50.1"},"reference-count":94,"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":"Australian Research Council Discovery Project","award":["DP190102443"],"award-info":[{"award-number":["DP190102443"]}]},{"name":"Office of National Intelligence National Intelligence Postdoctoral","award":["NIPG-2021-001"],"award-info":[{"award-number":["NIPG-2021-001"]}]},{"DOI":"10.13039\/100015539","name":"Australian Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015539","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.2022.3146005","type":"journal-article","created":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T20:31:47Z","timestamp":1643142707000},"page":"2309-2322","source":"Crossref","is-referenced-by-count":33,"title":["Dense Video Captioning With Early Linguistic Information Fusion"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2763-2094","authenticated-orcid":false,"given":"Nayyer","family":"Aafaq","sequence":"first","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, 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":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, 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":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, 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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00714"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1117"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep Learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_22"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940007"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3355390"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref92","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"Proc Anterior Cruciate Ligament Workshop"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref94","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Proc Text Summarization Branches Out"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref90","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref89","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref41","first-page":"1","article-title":"Temporal activity detection in untrimmed videos with recurrent neural networks","author":"montes","year":"0","journal-title":"Proc 1st NIPS Workshop Large Scale Comput Vis Syst"},{"key":"ref85","author":"oppenheim","year":"1999","journal-title":"Discrete-Time Signal Processing"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref87","article-title":"Layer normalization","volume":"1050","author":"ba","year":"2016","journal-title":"Statistics"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988435"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.780"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref82","article-title":"BERTScore: Evaluating text generation with bert","author":"zhang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref81","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1049"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref80","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc 16th Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.341"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3115\/981623.981633"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2934"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298735"},{"key":"ref31","article-title":"THUMOS challenge: Action recognition with a large number of classes","author":"gorban","year":"2015"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref77","article-title":"A synopsis of linguistic theory, 1930-1955","author":"firth","year":"0","journal-title":"Studies in Linguistic Analysis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.65"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1954.11659520"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref70","first-page":"3059","article-title":"Weakly supervised dense event captioning in videos","author":"duan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00900"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref69","first-page":"958","article-title":"Multi-modal dense video captioning","author":"iashin","year":"0","journal-title":"Proc IEEE Conf Comp Vis Pattern Recognit"},{"key":"ref20","first-page":"396","article-title":"Joint event detection and description in continuous video streams","author":"xu","year":"0","journal-title":"Proc IEEE Conf Appl Comput Vis"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12330"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09693415.pdf?arnumber=9693415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:43:34Z","timestamp":1687805014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9693415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3146005","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}