{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T14:42:54Z","timestamp":1793457774563,"version":"4.5.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcds.2024.3405573","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T17:57:54Z","timestamp":1717091874000},"page":"2032-2042","source":"Crossref","is-referenced-by-count":27,"title":["Control With Style: Style Embedding-Based Variational Autoencoder for Controlled Stylized Caption Generation Framework"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9218-2515","authenticated-orcid":false,"given":"Dhruv","family":"Sharma","sequence":"first","affiliation":[{"name":"Department of Electronics and Communication Engineering, Delhi Technological University, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3401-596X","authenticated-orcid":false,"given":"Chhavi","family":"Dhiman","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, Delhi Technological University, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3348-477X","authenticated-orcid":false,"given":"Dinesh","family":"Kumar","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, Delhi Technological University, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119773"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2020.115836"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_32"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428453"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10475"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01280"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475662"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref14","article-title":"Corpus-guided sentence generation of natural images","volume-title":"Proc. Empirical Methods Natural Language Process.","author":"Yang","year":"2011"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref16","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"Mao","year":"2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr31182.2015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00898"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/app9091886"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref26","article-title":"Improving image captioning descriptiveness by ranking and LLM-based fusion","author":"Bianco","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00559"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00433"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10475"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548295"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01636-2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612263"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00252"},{"key":"ref34","article-title":"On unifying deep generative models","author":"Hu","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref36","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Larsen","year":"2016"},{"key":"ref37","first-page":"3881","article-title":"Improved variational autoencoders for text modeling using dilated convolutions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"ref39","first-page":"2180","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2016"},{"key":"ref40","first-page":"5927","article-title":"Learning disentangled representations with semi-supervised deep generative models","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst. (NIPS)","author":"Siddharth","year":"2017"},{"key":"ref41","first-page":"1587","article-title":"Toward controlled generation of text","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Hu","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.inlg-1.5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2913372"},{"key":"ref45","article-title":"SMU: Smooth activation function for deep networks using smoothing maximum technique","author":"Biswas","year":"2022"},{"key":"ref46","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref48","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1002"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1041"},{"key":"ref51","article-title":"VAE based text style transfer with pivot words enhancement learning","author":"Xu","year":"2021"},{"key":"ref52","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1126\/science.7761831"},{"key":"ref54","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"Scott","year":"2014"},{"key":"ref55","article-title":"Adam: A method for stochastic","author":"Kingma","year":"2014"},{"key":"ref56","first-page":"311","article-title":": A method for automatic evaluation of machine","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni","year":"2002"},{"key":"ref57","first-page":"228","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Meas. Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/110"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10774064\/10542089.pdf?arnumber=10542089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T07:30:26Z","timestamp":1733297426000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10542089\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":60,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2024.3405573","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}