{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:00:10Z","timestamp":1743141610819,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030399047"},{"type":"electronic","value":"9783030399054"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-39905-4_7","type":"book-chapter","created":{"date-parts":[[2020,1,22]],"date-time":"2020-01-22T01:34:32Z","timestamp":1579656872000},"page":"62-74","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-to-Image Synthesis Based on\u00a0Machine Generated Captions"],"prefix":"10.1007","author":[{"given":"Marco","family":"Menardi","sequence":"first","affiliation":[]},{"given":"Alex","family":"Falcon","sequence":"additional","affiliation":[]},{"given":"Saida S.","family":"Mohamed","sequence":"additional","affiliation":[]},{"given":"Lorenzo","family":"Seidenari","sequence":"additional","affiliation":[]},{"given":"Giuseppe","family":"Serra","sequence":"additional","affiliation":[]},{"given":"Alberto","family":"Del Bimbo","sequence":"additional","affiliation":[]},{"given":"Carlo","family":"Tasso","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,1,22]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 95\u2013104 (2016)","DOI":"10.1109\/CVPR.2017.18"},{"issue":"2016","key":"7_CR2","first-page":"2172","volume":"29","author":"X Chen","year":"2016","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. Adv. Neural Inf. Process. Syst. 29(2016), 2172\u20132180 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"7_CR5","unstructured":"Denton, E.L., Chintala, S., Fergus, R., et al.: Deep generative image models using a Laplacian pyramid of adversarial networks. In: Advances in Neural Information Processing Systems, pp. 1486\u20131494 (2015)"},{"key":"7_CR6","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 2672\u20132680. Curran Associates, Inc. (2014)"},{"key":"7_CR7","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-supplementary material"},{"issue":"8","key":"7_CR8","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Hong, S., Yang, D., Choi, J., Lee, H.: Inferring semantic layout for hierarchical text-to-image synthesis. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7986\u20137994 (2018)","DOI":"10.1109\/CVPR.2018.00833"},{"issue":"6","key":"7_CR10","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1145\/3295748","volume":"51","author":"M Hossain","year":"2019","unstructured":"Hossain, M., Sohel, F., Shiratuddin, M.F., Laga, H.: A comprehensive survey of deep learning for image captioning. ACM Comput. Surv. (CSUR) 51(6), 118 (2019)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 5967\u20135976 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"7_CR13","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: 6th International Conference on Learning Representations, ICLR 2018 (2018)"},{"key":"7_CR14","unstructured":"Kiros, R., Zhu, Y., Salakhutdinov, R., Zemel, R.S., Urtasun, R., Torralba, A., Fidler, S.: Skip-thought vectors. In: Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, Montreal, Quebec, Canada, 7\u201312 December 2015, pp. 3294\u20133302 (2015). \nhttp:\/\/papers.nips.cc\/paper\/5950-skip-thought-vectors"},{"key":"7_CR15","unstructured":"Li, W., et al.: Object-driven text-to-image synthesis via adversarial training. CoRR abs\/1902.10740 (2019), \nhttp:\/\/arxiv.org\/abs\/1902.10740"},{"key":"7_CR16","unstructured":"Zhang, L., Sung, F., Liu, F., Xiang, T., Gong, S., Yang, Y., Hospedales, T.M.: Actor-critic sequence training for image captioning (2017)"},{"key":"7_CR17","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":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., 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). \nhttps:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"7_CR18","unstructured":"Mansimov, E., Parisotto, E., Ba, L.J., Salakhutdinov, R.: Generating images from captions with attention. In: 4th International Conference on Learning Representations, ICLR 2016, Conference Track Proceedings, San Juan, Puerto Rico, 2\u20134 May 2016 (2016). \nhttp:\/\/arxiv.org\/abs\/1511.02793"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Clune, J., Bengio, Y., Dosovitskiy, A., Yosinski, J.: Plug & play generative networks: conditional iterative generation of images in latent space. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 3510\u20133520 (2017)","DOI":"10.1109\/CVPR.2017.374"},{"key":"7_CR20","unstructured":"Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2642\u20132651. JMLR. org (2017)"},{"key":"7_CR21","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: MirrorGAN: learning text-to-image generation by redescription. CoRR abs\/1903.05854 (2019). \nhttp:\/\/arxiv.org\/abs\/1903.05854"},{"key":"7_CR22","unstructured":"Ranzato, M., Chopra, S., Auli, M., Zaremba, W.: Sequence level training with recurrent neural networks. In: 4th International Conference on Learning Representations, ICLR 2016 (2016)"},{"key":"7_CR23","doi-asserted-by":"publisher","unstructured":"Reed, S.E., Akata, Z., Lee, H., Schiele, B.: Learning deep representations of fine-grained visual descriptions. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 49\u201358 (2016). \nhttps:\/\/doi.org\/10.1109\/CVPR.2016.13","DOI":"10.1109\/CVPR.2016.13"},{"issue":"2016","key":"7_CR24","first-page":"217","volume":"29","author":"SE Reed","year":"2016","unstructured":"Reed, S.E., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. Adv. Neural Inf. Process. Syst. 29(2016), 217\u2013225 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"7_CR25","unstructured":"Reed, S.E., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, pp. 1060\u20131069 (2016)"},{"key":"7_CR26","unstructured":"Reed, S.E., Oord, A.v.d., Kalchbrenner, N., Bapst, V., Botvinick, M.M., Freitas, N.d.: Generating Interpretable Images with Controllable Structure (2017). \nhttps:\/\/www.semanticscholar.org\/paper\/Generating-Interpretable-Images-with-Controllable-Reed-Oord\/bd5c69fd9b34f481e03363f9d913c31af83547a5"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 1179\u20131195 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"issue":"2016","key":"7_CR28","first-page":"2226","volume":"29","author":"T Salimans","year":"2016","unstructured":"Salimans, T., Goodfellow, I.J., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. Adv. Neural Inf. Process. Syst. 29(2016), 2226\u20132234 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Shetty, R., Rohrbach, M., Hendricks, L.A., Fritz, M., Schiele, B.: Speaking the same language: matching machine to human captions by adversarial training. In: IEEE International Conference on Computer Vision, ICCV 2017, pp. 4155\u20134164 (2017)","DOI":"10.1109\/ICCV.2017.445"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"3-4","key":"7_CR31","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"Ronald J. Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992). \nhttp:\/\/link.springer.com\/10.1007\/BF00992696","journal-title":"Machine Learning"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"7_CR33","unstructured":"Yu, F., Zhang, Y., Song, S., Seff, A., Xiao, J.: LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. CoRR abs\/1506.0 (2015). \nhttp:\/\/arxiv.org\/abs\/1506.03365"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"7_CR35","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2018","unstructured":"Zhang, H., et al.: StackGAN++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 41, 1947\u20131962 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, Y., Yang, L.: Photographic text-to-image synthesis with a hierarchically-nested adversarial network. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, pp. 6199\u20136208 (2018)","DOI":"10.1109\/CVPR.2018.00649"},{"key":"7_CR37","unstructured":"Zhou, R., Xiaoyu, W., Ning, Z., Xutao, L., Li-Jia, L.: Deep reinforcement learning-based image captioning with embedding reward. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 1151\u20131159 (2017)"},{"key":"7_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/978-3-319-46454-1_36","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J-Y Zhu","year":"2016","unstructured":"Zhu, J.-Y., Kr\u00e4henb\u00fchl, P., Shechtman, E., Efros, A.A.: Generative visual manipulation on the natural image manifold. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 597\u2013613. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46454-1_36"}],"container-title":["Communications in Computer and Information Science","Digital Libraries: The Era of Big Data and Data Science"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-39905-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,19]],"date-time":"2020-05-19T15:00:52Z","timestamp":1589900452000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-39905-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030399047","9783030399054"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-39905-4_7","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"22 January 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IRCDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italian Research Conference on Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bari","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 January 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ircdl2020a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/kdde.di.uniba.it\/ircdl20\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","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":"12","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":"6","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":"46% - 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":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}