{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:25:04Z","timestamp":1740101104441,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,28]],"date-time":"2022-05-28T00:00:00Z","timestamp":1653696000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,28]],"date-time":"2022-05-28T00:00:00Z","timestamp":1653696000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,28]]},"DOI":"10.1109\/iscas48785.2022.9937712","type":"proceedings-article","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:38:08Z","timestamp":1668199088000},"page":"2993-2997","source":"Crossref","is-referenced-by-count":0,"title":["Multi-concept Mining for Video Captioning Based on Multiple Tasks"],"prefix":"10.1109","author":[{"given":"Qinyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Tongji University,Department of Computer Science & Technology,Shanghai,P. R. China"}]},{"given":"Pengjie","family":"Tang","sequence":"additional","affiliation":[{"name":"Jinggangshan University,College of Electronic and Information Engineering,Ji’an,P. R. China"}]},{"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science & Technology,Shanghai,P. R. China"}]},{"given":"Jinjing","family":"Gu","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science & Technology,Shanghai,P. R. China"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref32","first-page":"936","article-title":"Guided open vocabulary image captioning with constrained beam search","author":"erson","year":"2017","journal-title":"Proc EMNLP’17"},{"key":"ref31","article-title":"Super-convergence: Very fast training of residual networks using large learning rates","author":"leslie","year":"2017","journal-title":"arXiv 1708 07120"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR’15"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","first-page":"495","article-title":"3D convolutional neural networks for human action recognition","author":"ji","year":"2010","journal-title":"Proc ICCV’15"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref14","first-page":"847","article-title":"TVT: Two-view transformer network for video captioning","author":"chen","year":"2018","journal-title":"Proc ACML’18"},{"key":"ref15","first-page":"12487","article-title":"Spatiotemporal dynamics and semantic attribute enriched visual encoding for video captioning","author":"aafaq","year":"2019","journal-title":"Proc CVPR’19"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/88"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref28","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc ACL’04 Workshop"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"ref27","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL’05"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"ren","year":"2015","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref5","article-title":"A short note about Kinetics-600","author":"carreira","year":"2018","journal-title":"arXiv 1808 01340"},{"key":"ref8","article-title":"Asymmetric loss for multi-label classification","author":"baruch","year":"2021","journal-title":"arXiv 2009 14119"},{"key":"ref7","article-title":"The Open Images dataset V4","author":"kuznetsova","year":"2018","journal-title":"arXiv 1811 00982"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref1","first-page":"10524","article-title":"On layer normalization in the transformer architecture","author":"xiong","year":"2020","journal-title":"Proc ICML’20"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref24","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc ACL’11"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref26","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL’02"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"}],"event":{"name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2022,5,27]]},"location":"Austin, TX, USA","end":{"date-parts":[[2022,6,1]]}},"container-title":["2022 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9937201\/9937203\/09937712.pdf?arnumber=9937712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T20:20:47Z","timestamp":1669666847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9937712\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,28]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iscas48785.2022.9937712","relation":{},"subject":[],"published":{"date-parts":[[2022,5,28]]}}}