{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T11:38:18Z","timestamp":1783510698857,"version":"3.55.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1109\/tcsvt.2020.3036860","type":"journal-article","created":{"date-parts":[[2020,11,9]],"date-time":"2020-11-09T21:53:52Z","timestamp":1604958832000},"page":"3118-3127","source":"Crossref","is-referenced-by-count":62,"title":["Noise Augmented Double-Stream Graph Convolutional Networks for Image Captioning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-3597","authenticated-orcid":false,"given":"Lingxiang","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5436-6233","authenticated-orcid":false,"given":"Min","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Sang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7587-101X","authenticated-orcid":false,"given":"Ting","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7732","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref72","article-title":"Knowing when to look: Adaptive attention via a visual sentinel for image captioning","author":"lu","year":"2016","journal-title":"arXiv 1612 01887"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_21"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3020877"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018650"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/84"},{"key":"ref30","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref35","first-page":"1","article-title":"Temporal-difference learning with sampling baseline for image captioning","author":"chen","year":"2018","journal-title":"Proc AAAI"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref60","first-page":"2702","article-title":"Discriminative embeddings of latent variable models for structured data","author":"dai","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref62","article-title":"Noisy parallel approximate decoding for conditional recurrent language model","author":"cho","year":"2016","journal-title":"arXiv 1605 03835"},{"key":"ref61","first-page":"4800","article-title":"Hierarchical graph representation learning with differentiable pooling","author":"ying","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref63","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref64","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-018-9581-x"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref66","first-page":"1","article-title":"Rouge: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"2004","journal-title":"Proc Text Summarization Branches Out ACL Workshop"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2965966"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.306"},{"key":"ref21","first-page":"220","article-title":"Composing simple image descriptions using web-scale N-Grams","author":"li","year":"2011","journal-title":"Proc 15th Conf Comput Natural Language Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2931815"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref25","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":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1159"},{"key":"ref58","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref54","first-page":"1","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"Proc ICLR"},{"key":"ref53","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928144"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00756"},{"key":"ref40","first-page":"1","article-title":"Memory networks","author":"weston","year":"2015","journal-title":"Proc ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref14","first-page":"2","article-title":"Parameter space noise for exploration","author":"plappert","year":"2018","journal-title":"Proc ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/72.548170"},{"key":"ref16","article-title":"Adding gradient noise improves learning for very deep networks","author":"neelakantan","year":"2015","journal-title":"arXiv 1511 06807"},{"key":"ref17","first-page":"3059","article-title":"Noisy activation functions","author":"gulcehre","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2906226"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2936526"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3007330"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00683"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855406"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855415"},{"key":"ref46","first-page":"3189","article-title":"Learning shape correspondence with anisotropic convolutional neural networks","author":"boscaini","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"ref48","first-page":"8344","article-title":"Learning conditioned graph structures for interpretable visual question answering","author":"norcliffe-brown","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","first-page":"1","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"yan","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref44","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"defferrard","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc ICLR"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9505291\/09252928.pdf?arnumber=9252928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:24Z","timestamp":1652194224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9252928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":72,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.3036860","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8]]}}}