{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T15:05:40Z","timestamp":1771599940130,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3021857","type":"journal-article","created":{"date-parts":[[2020,9,4]],"date-time":"2020-09-04T21:01:40Z","timestamp":1599253300000},"page":"169146-169159","source":"Crossref","is-referenced-by-count":12,"title":["Understanding Objects in Video: Object-Oriented Video Captioning via Structured Trajectory and Adversarial Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8072-4866","authenticated-orcid":false,"given":"Fangyi","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8877-2421","authenticated-orcid":false,"given":"Jenq-Neng","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-2488","authenticated-orcid":false,"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1762-3648","authenticated-orcid":false,"given":"Guang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9045-1339","authenticated-orcid":false,"given":"Jun","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00629"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855422"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2018.8363576"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref36","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref35","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3355390"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"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 Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref26","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc of Workshop on Text Summarization Branches Out"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.013"},{"key":"ref51","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref55","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume":"1","author":"chen","year":"2011","journal-title":"Proc Annu Meeting Assoc Comput Linguist Conf Human Lang Technol"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350853"},{"key":"ref52","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref11","article-title":"Attention correctness in neural image captioning","author":"liu","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref16","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"venugopalan","year":"2014","journal-title":"arXiv preprint arXiv 1412 4729"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2767557"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.07.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2879642"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817538"},{"key":"ref8","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref49","article-title":"CyCADA: Cycle-consistent adversarial domain adaptation","author":"hoffman","year":"2017","journal-title":"arXiv 1711 03213"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref46","article-title":"Adversarial learning for semi-supervised semantic segmentation","author":"hung","year":"2018","journal-title":"arXiv 1802 07934"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00780"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref42","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv 1411 1784"},{"key":"ref41","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09186666.pdf?arnumber=9186666","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:42Z","timestamp":1639770942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9186666\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3021857","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}