{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:05:25Z","timestamp":1742947525336,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031585340"},{"type":"electronic","value":"9783031585357"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-58535-7_31","type":"book-chapter","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T17:01:50Z","timestamp":1719939710000},"page":"375-385","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improved Image Captioning Using GAN and\u00a0ViT"],"prefix":"10.1007","author":[{"given":"Vrushank D.","family":"Rao","sequence":"first","affiliation":[]},{"given":"B. N.","family":"Shashank","sequence":"additional","affiliation":[]},{"given":"S.","family":"Nagesh Bhattu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,3]]},"reference":[{"key":"31_CR1","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"31_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"31_CR3","unstructured":"Xu, K., et al.: Neural image caption generation with visual attention. In Proceedings ICML, pp. 2048\u20132057 (2015)"},{"key":"31_CR4","unstructured":"Jiang, Y., Chang, S., Wang, Z.: TransGAN: two pure transformers can make one strong GAN, and that can scale up. In: Advances in Neural Information Processing Systems, vol. 34, pp. 14745\u201314758 (2021)"},{"key":"31_CR5","doi-asserted-by":"publisher","unstructured":"Dai, B. Fidler, S., Urtasun, R., Lin, D.: Towards diverse and natural image descriptions via a conditional GAN. In: 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 2989\u20132998 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.323","DOI":"10.1109\/ICCV.2017.323"},{"key":"31_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/978-3-030-58568-6_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zhong","year":"2020","unstructured":"Zhong, Y., Wang, L., Chen, J., Yu, D., Li, Y.: Comprehensive image captioning via scene graph decomposition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 211\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_13"},{"key":"31_CR7","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.: Multimodal neural language models. In: Proceedings of the 31st International Conference on International Conference on Machine Learning (ICML 2014), vol. 32, pp. II-595\u2013II-603. JMLR.org (2014)"},{"key":"31_CR8","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: a general framework for self-supervised learning in speech, vision and language. In: International Conference on Machine Learning, pp. 1298\u20131312 (2022)"},{"key":"31_CR9","doi-asserted-by":"publisher","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, pp. 3156\u20133164 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298935","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"31_CR10","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1016\/j.neuroimage.2018.03.045","volume":"174","author":"Y Wang","year":"2018","unstructured":"Wang, Y., et al.: 3D conditional generative adversarial networks for high-quality PET image estimation at low dose. Neuroimage 174, 550\u2013562 (2018)","journal-title":"Neuroimage"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"31_CR12","unstructured":"Rashtchian, C., Young, P., Hodosh, M., Hockenmaier, J.: Collecting image annotations using amazon\u2019s mechanical turk. In: Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon\u2019s Mechanical Turk, pp. 139\u2013147 (2010)"},{"key":"31_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L T-Y","year":"2014","unstructured":"T-Y, L., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"31_CR15","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation AND\/OR Summarization, pp. 65\u201372 (2005)"},{"key":"31_CR16","unstructured":"Lin, C.-Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"31_CR18","unstructured":"Parmar, N., et al.: Image transformer. In International Conference on Machine Learning, pp. 4055\u20134064 (2018)"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"issue":"25","key":"31_CR20","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1049\/el.2017.3159","volume":"53","author":"J Wu","year":"2017","unstructured":"Wu, J., Hu, H.: Cascade recurrent neural network for image caption generation. Electron. Lett. 53(25), 1642\u20131643 (2017)","journal-title":"Electron. Lett."},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"31_CR22","unstructured":"Liu, W., Chen, S., Guo, L., Zhu, X., Liu, J.: CPTR: full transformer network for image captioning. arXiv preprint arXiv:2101.10804 (2021)"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: Dual-level collaborative transformer for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 3, pp. 2286\u20132293 (2021)","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"31_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"}],"container-title":["Communications in Computer and Information Science","Computer Vision and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-58535-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T17:09:12Z","timestamp":1719940152000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-58535-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031585340","9783031585357"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-58535-7_31","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jammu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iitjammu.ac.in\/cvip2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Online CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"461","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"140","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}