{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:46:13Z","timestamp":1740181573236,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T00:00:00Z","timestamp":1711497600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T00:00:00Z","timestamp":1711497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-024-02609-7","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T14:01:42Z","timestamp":1711548102000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimized Mirror Generative Adversarial Network with BERT Neural Architecture for Text Caption to Image Conversion"],"prefix":"10.1007","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6636-4219","authenticated-orcid":false,"given":"Ashish","family":"Sharma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaurav","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatima A.","family":"Asiri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javed Khan","family":"Bhutto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdulwasa Bakr","family":"Barnawi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,27]]},"reference":[{"unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J. Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems. 2013; p. 26.","key":"2609_CR1"},{"unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Generative adversarial nets. In: Advances in Neural Information Processing Systems. 2014;p. 27.","key":"2609_CR2"},{"unstructured":"Herdade S, Kappeler A, Boakye K, Soares J. Image captioning: Transforming objects into words. In: Advances in Neural Information Processing Systems; 2019. pp. 11135\u201311145.","key":"2609_CR3"},{"doi-asserted-by":"crossref","unstructured":"Zhang H, Xu T, Li H, Zhang S, Wang X, Huang X, Metaxas DN. Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In: The IEEE International Conference on Computer Vision (ICCV); 2017.","key":"2609_CR4","DOI":"10.1109\/ICCV.2017.629"},{"issue":"8","key":"2609_CR5","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2019","unstructured":"Zhang H, Xu T, Li H, Zhang S, Wang X, Huang X, Metaxas DN. Stackgan++: Realistic image synthesis with stacked generative adversarial networks. IEEE Trans Pattern Anal Mach Intell. 2019;41(8):1947\u201362.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"doi-asserted-by":"crossref","unstructured":"Xu T, Zhang P, Huang Q, Zhang H, Gan Z, Huang X, He X. Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2018.","key":"2609_CR6","DOI":"10.1109\/CVPR.2018.00143"},{"doi-asserted-by":"crossref","unstructured":"Qiao T, Zhang J, Xu D, Tao D. Mirrorgan: Learning text-to-image generation by redescription. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2019.","key":"2609_CR7","DOI":"10.1109\/CVPR.2019.00160"},{"unstructured":"Chen X, Qing L, He X, Luo X, Xu Y. FTGAN: A fully-trained generative adversarial networks for text to face generation. CoRR. 2019. arXiv: 1904.05729","key":"2609_CR8"},{"unstructured":"Reed S, Akata Z, Yan X, Logeswaran L, Schiele B, Lee H. Generative adversarial text to image synthesis. arXiv preprint arXiv:1605.05396. 2016.","key":"2609_CR9"},{"doi-asserted-by":"crossref","unstructured":"Yan X, Yang J, Sohn K, Lee H. Attribute2image: Conditional image generation from visual attributes. In: European Conference on Computer Vision. Springer; 2016. pp. 776\u2013791.","key":"2609_CR10","DOI":"10.1007\/978-3-319-46493-0_47"},{"unstructured":"Odena A, Olah C, Shlens J. Conditional image synthesis with auxiliary classifier gans. In: Proceedings of the 34th International Conference on Machine Learning; 2017:70, pp. 2642\u20132651. JMLR.org","key":"2609_CR11"},{"doi-asserted-by":"crossref","unstructured":"Lu Y, Tai Y-W, Tang C-K. Attribute-guided face generation using conditional cyclegan. In: Proceedings of the European Conference on Computer Vision (ECCV), 2018;pp. 282\u2013297","key":"2609_CR12","DOI":"10.1007\/978-3-030-01258-8_18"},{"key":"2609_CR13","first-page":"4790","volume-title":"Advances in neural information processing systems","author":"A Oord","year":"2016","unstructured":"Oord A, Kalchbrenner N, Espeholt L, Kavukcuoglu K, Vinyals O, Graves A. Conditional image generation with pixelcnn decoders. In: Lee DD, Sugiyama M, Luxburg UV, Guyon I, Garnett R, editors. Advances in neural information processing systems, vol. 29. New York: Curran Associates Inc.; 2016. p. 4790\u20138."},{"doi-asserted-by":"crossref","unstructured":"Castelle M. The social lives of generative adversarial networks. In: FAT*, p. 413; 2020.","key":"2609_CR14","DOI":"10.1145\/3351095.3373156"},{"unstructured":"Gui J, Sun Z, Wen Y, Tao D, Ye J. A review on generative adversarial networks: Algorithms, theory, and applications. arXiv preprint arXiv:2001.06937. 2020.","key":"2609_CR15"},{"issue":"11","key":"2609_CR16","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster M, Paliwal KK. Bidirectional recurrent neural networks. IEEE Trans Signal Process. 1997;45(11):2673\u201381.","journal-title":"IEEE Trans Signal Process"},{"doi-asserted-by":"crossref","unstructured":"Cheng J, Chen Y-PP, Li M, Jiang Y-G. Tc-gan: Triangle cycle-consistent gans for face frontalization with facial features preserved. In: Proceedings of the 27th ACM International Conference on Multimedia; 2019. pp. 220\u2013228.","key":"2609_CR17","DOI":"10.1145\/3343031.3351031"},{"unstructured":"Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434, 2016.","key":"2609_CR18"},{"unstructured":"Arjovsky M, Chintala S, Bottou L. Wasserstein GAN. 2017.","key":"2609_CR19"},{"unstructured":"Karras T, Aila T, Laine S, Lehtinen J. Progressive growing of GANs for improved quality, stability, and variation. arXiv:1710.10196, 2018.","key":"2609_CR20"},{"doi-asserted-by":"publisher","unstructured":"Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16\u201320, 2019, pp. 4401\u20134410. Computer Vision Foundation \/ IEEE. 2019. https:\/\/doi.org\/10.1109\/CVPR.2019.00453 . http:\/\/openaccess.thecvf.com\/content_CVPR_2019\/html\/Karras_A_Style-Based_Generator_Architecture_for_Generative_Adversarial_Networks_CVPR_2019_paper.html","key":"2609_CR21","DOI":"10.1109\/CVPR.2019.00453"},{"unstructured":"Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S. Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R , editors. Advances in Neural Information Processing Systems 30, 2017;pp. 6626\u20136637.","key":"2609_CR22"},{"doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J. Facenet: A unified embedding for face recognition and clustering. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2015.","key":"2609_CR23","DOI":"10.1109\/CVPR.2015.7298682"},{"doi-asserted-by":"crossref","unstructured":"Cho K, Merrienboer B, G\u00fcl\u00e7ehre \u00c7, Bougares F, Schwenk H, Bengio Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. CoRR. 2014. arXiv: 1406.1078","key":"2609_CR24","DOI":"10.3115\/v1\/D14-1179"},{"doi-asserted-by":"publisher","unstructured":"Rice JR. The algorithm selection problem**this work was partially supported by the national science foundation through grant gp-32940x. this chapter was presented as the george e. forsythe memorial lecture at the computer science conference, February 19, 1975, Washington, D. D. Advances in Computers, vol. 15, pp. 65\u2013118. Elsevier. 1976. https:\/\/doi.org\/10.1016\/S0065-2458(08)60520-3 . https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0065245808605203","key":"2609_CR25","DOI":"10.1016\/S0065-2458(08)60520-3"},{"unstructured":"Devlin J, Chang M, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. CoRR; 2018.","key":"2609_CR26"},{"unstructured":"Ramos J. Using tf-idf to determine word relevance in document queries. In: Proceedings of the First Instructional Conference on Machine Learning. Piscataway, NJ; 2003. vol. 242, pp. 133\u2013142","key":"2609_CR27"},{"doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD. Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP); 2014. pp. 1532\u20131543.","key":"2609_CR28","DOI":"10.3115\/v1\/D14-1162"},{"doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I. Sentence-bert: Sentence embeddings using Siamese Bert-networks. arXiv preprint arXiv:1908.10084; 2019.","key":"2609_CR29","DOI":"10.18653\/v1\/D19-1410"},{"doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016.","key":"2609_CR30","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Hong S, Yang D, Choi J, Lee H. Inferring semantic layout for hierarchical text-to-image synthesis. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2018.","key":"2609_CR31","DOI":"10.1109\/CVPR.2018.00833"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-024-02609-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-024-02609-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-024-02609-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T14:05:56Z","timestamp":1711548356000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-024-02609-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,27]]},"references-count":31,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["2609"],"URL":"https:\/\/doi.org\/10.1007\/s42979-024-02609-7","relation":{},"ISSN":["2661-8907"],"issn-type":[{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2024,3,27]]},"assertion":[{"value":"3 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors of the manuscript entitled \u201cOptimized Mirror Generative Adversarial Network with BERT Neural Architecture for Text Caption to Image Conversion\u201d; there is no conflict of interest. On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"334"}}