{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:40:54Z","timestamp":1777128054093,"version":"3.51.4"},"reference-count":65,"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"}],"funder":[{"name":"Fundamental Research Funds for the Central University, China","award":["FRF-BD-20-11A"],"award-info":[{"award-number":["FRF-BD-20-11A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3307972","type":"journal-article","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T18:01:43Z","timestamp":1692813703000},"page":"3164-3179","source":"Crossref","is-referenced-by-count":4,"title":["Global-Shared Text Representation Based Multi-Stage Fusion Transformer Network for Multi-Modal Dense Video Captioning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0764-6579","authenticated-orcid":false,"given":"Yulai","family":"Xie","sequence":"first","affiliation":[{"name":"Hitachi China Research Laboratory, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9515-1079","authenticated-orcid":false,"given":"Jingjing","family":"Niu","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0523-8478","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hitachi China Research Laboratory, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2251-9220","authenticated-orcid":false,"given":"Fang","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.83"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-896"},{"key":"ref3","article-title":"Weighted transformer network for machine translation","author":"Ahmed","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.515"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298878"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","first-page":"1","article-title":"A better use of audio-visual cues: Dense video captioning with bi-modal transformer","volume-title":"Proc. 31st Brit. Mach. Vis. Conf.","author":"Iashin"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00911"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"ref11","article-title":"Multi-modal dense video captioning","author":"Iashin","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00900"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1641"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/k19-1039"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ipec54454.2022.9777333"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-2125"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17534"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1208"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1142\/S021800142255014X"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1656"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.02.028"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1115"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref30","first-page":"7136","article-title":"AMOA: Global acoustic feature enhanced modal-order-aware network for multimodal sentiment analysis","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479919"},{"key":"ref32","first-page":"22605","article-title":"COOT: Cooperative hierarchical transformer for video-text representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ging"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref35","article-title":"See, hear, and read: Deep aligned representations","author":"Aytar","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/n15-1173"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.117"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.012"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00854"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/access.2018.2879642"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00443"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01252-6_29","article-title":"Move forward and tell: A progressive generator of video descriptions","author":"Xiong","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.496"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00676"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref47","first-page":"139","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00675"},{"key":"ref50","first-page":"3059","article-title":"Weakly supervised dense event captioning in videos","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Duan"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12330"},{"key":"ref52","article-title":"An attempt towards interpretable audio-visual video captioning","author":"Tian","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/asru.2017.8268968"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/icarm.2019.8834066"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952132"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.502"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1162"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00972"},{"key":"ref59","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref60","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/w14-3348"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref64","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2798607"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10227555.pdf?arnumber=10227555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T21:36:02Z","timestamp":1709328962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10227555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3307972","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}