{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:21:20Z","timestamp":1778347280732,"version":"3.51.4"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031208614","type":"print"},{"value":"9783031208621","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20862-1_25","type":"book-chapter","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:29:12Z","timestamp":1667518152000},"page":"339-350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Obj-SA-GAN: Object-Driven Text-to-Image Synthesis with\u00a0Self-Attention Based Full Semantic Information Mining"],"prefix":"10.1007","author":[{"given":"Ruijun","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9215-4979","authenticated-orcid":false,"given":"Weihua","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8917-2196","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1214-6317","authenticated-orcid":false,"given":"Quan","family":"Bai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"issue":"4","key":"25_CR1","volume":"10","author":"J Agnese","year":"2020","unstructured":"Agnese, J., Herrera, J., Tao, H., Zhu, X.: A survey and taxonomy of adversarial neural networks for text-to-image synthesis. Wiley Interdisc. Rev.: Data Mining Knowl. Discovery 10(4), e1345 (2020)","journal-title":"Wiley Interdisc. Rev.: Data Mining Knowl. Discovery"},{"key":"25_CR2","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.neucom.2018.05.080","volume":"311","author":"S Bai","year":"2018","unstructured":"Bai, S., An, S.: A survey on automatic image caption generation. Neurocomputing 311, 291\u2013304 (2018)","journal-title":"Neurocomputing"},{"key":"25_CR3","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":"25_CR4","doi-asserted-by":"publisher","unstructured":"Esfahani, S.N., Latifi, S.: Image generation with gans-based techniques: A survey. Int. J. of Comput. Sci. Inf. Technol. 11, 33\u201350 (10 2019). https:\/\/doi.org\/10.5121\/ijcsit.2019.11503","DOI":"10.5121\/ijcsit.2019.11503"},{"key":"25_CR5","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.neunet.2021.07.019","volume":"144","author":"S Frolov","year":"2021","unstructured":"Frolov, S., Hinz, T., Raue, F., Hees, J., Dengel, A.: Adversarial text-to-image synthesis: A review. Neural Netw. 144, 187\u2013209 (2021)","journal-title":"Neural Netw."},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Ghosh, B., Dutta, I.K., Totaro, M., Bayoumi, M.: A survey on the progression and performance of generative adversarial networks. In: 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/ICCCNT49239.2020.9225510"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Hong, S., Yang, D., Choi, J., Lee, H.: Inferring semantic layout for hierarchical text-to-image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7986\u20137994 (2018)","DOI":"10.1109\/CVPR.2018.00833"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, Y., Poursaeed, O., Hopcroft, J., Belongie, S.: Stacked generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern recognition, pp. 5077\u20135086 (2017)","DOI":"10.1109\/CVPR.2017.202"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Lee, H., Ullah, U., Lee, J.S., Jeong, B., Choi, H.C.: A brief survey of text driven image generation and maniulation. In: 2021 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), pp. 1\u20134. IEEE (2021)","DOI":"10.1109\/ICCE-Asia53811.2021.9641929"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Object-driven text-to-image synthesis via adversarial training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12174\u201312182 (2019)","DOI":"10.1109\/CVPR.2019.01245"},{"key":"25_CR12","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). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Ning, X., Nan, F., Xu, S., Yu, L., Zhang, L.: Multi-view frontal face image generation: a survey. Concurrency and Computation: Practice and Experience, p. e6147 (2020)","DOI":"10.1002\/cpe.6147"},{"issue":"1","key":"25_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13735-020-00196-w","volume":"10","author":"M Pavan Kumar","year":"2021","unstructured":"Pavan Kumar, M., Jayagopal, P.: Generative adversarial networks: a survey on applications and challenges. Int. J. Multimedia Inform. Retrieval 10(1), 1\u201324 (2021)","journal-title":"Int. J. Multimedia Inform. Retrieval"},{"key":"25_CR15","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International conference on machine learning, pp. 1060\u20131069. PMLR (2016)"},{"key":"25_CR16","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning, pp. 1060\u20131069. PMLR (2016)"},{"key":"25_CR17","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.inffus.2021.02.014","volume":"72","author":"P Shamsolmoali","year":"2021","unstructured":"Shamsolmoali, P., et al.: Image synthesis with adversarial networks: a comprehensive survey and case studies. Inform. Fusion 72, 126\u2013146 (2021)","journal-title":"Inform. Fusion"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Singh, N.K., Raza, K.: Medical image generation using generative adversarial networks: a review. Health Informatics: A Computational Perspective in Healthcare, pp. 77\u201396 (2021)","DOI":"10.1007\/978-981-15-9735-0_5"},{"key":"25_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in neural information processing systems, vol. 30 (2017)"},{"key":"25_CR20","unstructured":"Wang, F., Tax, D.M.: Survey on the attention based rnn model and its applications in computer vision. arXiv preprint arXiv:1601.06823 (2016)"},{"issue":"6","key":"25_CR21","doi-asserted-by":"publisher","first-page":"660","DOI":"10.23919\/TST.2017.8195348","volume":"22","author":"X Wu","year":"2017","unstructured":"Wu, X., Xu, K., Hall, P.: A survey of image synthesis and editing with generative adversarial networks. Tsinghua Sci. Technol. 22(6), 660\u2013674 (2017)","journal-title":"Tsinghua Sci. Technol."},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"25_CR23","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International Conference on Machine Learning, pp. 7354\u20137363. PMLR (2019)"},{"key":"25_CR24","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, pp. 5907\u20135915 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"issue":"8","key":"25_CR25","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(8), 1947\u20131962 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-030-00764-5_38","volume-title":"Advances in Multimedia Information Processing \u2013 PCM 2018","author":"S Zhang","year":"2018","unstructured":"Zhang, S., et al.: Text-to-image synthesis via visual-memory creative adversarial network. In: Hong, R., Cheng, W.-H., Yamasaki, T., Wang, M., Ngo, C.-W. (eds.) PCM 2018. LNCS, vol. 11166, pp. 417\u2013427. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00764-5_38"},{"key":"25_CR27","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/j.neucom.2021.04.069","volume":"451","author":"R Zhou","year":"2021","unstructured":"Zhou, R., Jiang, C., Xu, Q.: A survey on generative adversarial network-based text-to-image synthesis. Neurocomputing 451, 316\u2013336 (2021)","journal-title":"Neurocomputing"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Shimada, N.: Generative adversarial network for text-to-face synthesis and manipulation with pretrained bert model. In: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pp. 01\u201308. IEEE (2021)","DOI":"10.1109\/FG52635.2021.9666791"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, B., Ngo, C.W.: Cookgan: Causality based text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5519\u20135527 (2020)","DOI":"10.1109\/CVPR42600.2020.00556"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Yang, Y.: Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5802\u20135810 (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2022: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20862-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:34:14Z","timestamp":1667518454000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20862-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031208614","9783031208621"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20862-1_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"4 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shangai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pricai.org\/2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"432","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":"91","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":"39","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":"21% - 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":"7-8","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":"n\/a","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}