{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T11:38:26Z","timestamp":1783510706611,"version":"3.55.0"},"reference-count":73,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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","award":["61572140"],"award-info":[{"award-number":["61572140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976057"],"award-info":[{"award-number":["61976057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal R&D Foundation","award":["17DZ1100504"],"award-info":[{"award-number":["17DZ1100504"]}]},{"name":"Shanghai Municipal R&D Foundation","award":["16JC1420401"],"award-info":[{"award-number":["16JC1420401"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["19ZR1417200"],"award-info":[{"award-number":["19ZR1417200"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Humanities and Social Sciences Planning Fund of Ministry of Education of China","award":["19YJA630116"],"award-info":[{"award-number":["19YJA630116"]}]},{"DOI":"10.13039\/100008893","name":"University of Iowa","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008893","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2019.2928144","type":"journal-article","created":{"date-parts":[[2019,7,17]],"date-time":"2019-07-17T20:12:28Z","timestamp":1563394348000},"page":"694-709","source":"Crossref","is-referenced-by-count":70,"title":["Re-Caption: Saliency-Enhanced Image Captioning Through Two-Phase Learning"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8394-1698","authenticated-orcid":false,"given":"Lian","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7993-7223","authenticated-orcid":false,"given":"Yuejie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7561-0143","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1272-5538","authenticated-orcid":false,"given":"Weiguo","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref72","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":"ref71","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref70","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710620"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2602079"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.334"},{"key":"ref32","article-title":"Actor-critic sequence training for image captioning","author":"zhang","year":"2017","journal-title":"arXiv 1706 09601"},{"key":"ref31","first-page":"1","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref30","first-page":"5068","article-title":"Teaching machines to describe images with natural language feedback","author":"ling","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2817047"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2851672"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7_10"},{"key":"ref62","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref28","first-page":"3981","article-title":"Reference based LSTM for image captioning","author":"chen","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref64","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"4233","article-title":"Text-guided attention model for image captioning","author":"mun","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref65","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.272"},{"key":"ref67","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 at ACL"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref2","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref1","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/563"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855415"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.39"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/97"},{"key":"ref59","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126717"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"ref56","article-title":"Seeing with humans: Gaze-assisted neural image captioning","author":"sugano","year":"2016","journal-title":"arXiv 1608 05203"},{"key":"ref55","first-page":"6024","article-title":"CapSal: Leveraging captioning to boost semantics for salient object detection","author":"zhang","year":"2019","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref54","first-page":"8554","article-title":"Shifting more attention to video salient object detection","author":"fan","year":"2019","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref53","first-page":"196","article-title":"Salient objects in clutter: Bringing salient object detection to the foreground","author":"fan","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487833"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2834826"},{"key":"ref12","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref13","first-page":"1292","article-title":"Image description using visual dependency representations","author":"elliott","year":"2013","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref14","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proc 13th Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref15","article-title":"Exploring nearest neighbor approaches for image captioning","author":"devlin","year":"2015","journal-title":"arXiv 1505 04467"},{"key":"ref16","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855406"},{"key":"ref19","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref3","first-page":"6837","article-title":"Stack-captioning: Coarse-to-fine learning for image captioning","author":"gu","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref5","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3177745"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.433"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00326"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601784"},{"key":"ref42","first-page":"6943","article-title":"Recurrently aggregating deep features for salient object detection","author":"hu","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.399"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00081"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/95"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/08765586.pdf?arnumber=8765586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:11Z","timestamp":1651070351000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8765586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tip.2019.2928144","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}