{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:56:31Z","timestamp":1783526191562,"version":"3.55.0"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030926588","type":"print"},{"value":"9783030926595","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-92659-5_23","type":"book-chapter","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T07:09:18Z","timestamp":1642057758000},"page":"361-375","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["AttrLostGAN: Attribute Controlled Image Synthesis from\u00a0Reconfigurable Layout and\u00a0Style"],"prefix":"10.1007","author":[{"given":"Stanislav","family":"Frolov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avneesh","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00f6rn","family":"Hees","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tushar","family":"Karayil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Raue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Dengel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,13]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Ashual, O., Wolf, L.: Specifying object attributes and relations in interactive scene generation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4561\u20134569 (2019)","DOI":"10.1109\/ICCV.2019.00466"},{"key":"23_CR2","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2018.10.009","volume":"179","author":"A Borji","year":"2018","unstructured":"Borji, A.: Pros and cons of GAN evaluation measures. Comput. Vis. Image Underst. 179, 41\u201365 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"23_CR3","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (2018)"},{"key":"23_CR4","unstructured":"Choi, H.S., Park, C.D., Lee, K.: From inference to generation: end-to-end fully self-supervised generation of human face from speech. In: International Conference on Learning Representations (2020)"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 8789\u20138797 (2018)","DOI":"10.1109\/CVPR.2018.00916"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Dong, H., Yu, S., Wu, C., Guo, Y.: Semantic image synthesis via adversarial learning. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.608"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Frolov, S., Hinz, T., Raue, F., Hees, J., Dengel, A.: Adversarial text-to-image synthesis: a review. arXiv:2101.09983 (2021)","DOI":"10.1016\/j.neunet.2021.07.019"},{"key":"23_CR8","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR10","unstructured":"Henaff, M., Bruna, J., LeCun, Y.: Deep convolutional networks on graph-structured data. arXiv:1506.05163 (2015)"},{"key":"23_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-58574-7_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Herzig","year":"2020","unstructured":"Herzig, R., Bar, A., Xu, H., Chechik, G., Darrell, T., Globerson, A.: Learning canonical representations for scene graph to image generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 210\u2013227. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_13"},{"key":"23_CR12","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: Advances in Neural Information Processing Systems, pp. 6626\u20136637 (2017)"},{"key":"23_CR13","unstructured":"Hinz, T., Heinrich, S., Wermter, S.: Generating multiple objects at spatially distinct locations. In: International Conference on Learning Representations (2019)"},{"key":"23_CR14","first-page":"1","volume":"14","author":"T Hinz","year":"2020","unstructured":"Hinz, T., Heinrich, S., Wermter, S.: Semantic object accuracy for generative text-to-image synthesis. IEEE Trans. Pattern Anal. Mach. Intell. 14, 1\u201314 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR15","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 Computer Vision and Pattern Recognition, pp. 7986\u20137994 (2018)","DOI":"10.1109\/CVPR.2018.00833"},{"key":"23_CR16","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2016)","DOI":"10.1109\/CVPR.2017.632"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 1219\u20131228 (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"23_CR19","unstructured":"Karacan, L., Akata, Z., Erdem, A., Erdem, E.: Learning to generate images of outdoor scenes from attributes and semantic layouts. arXiv:1612.00215 (2016)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2018)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"23_CR21","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. CoRR arXiv:1312.6114 (2013)"},{"issue":"1","key":"23_CR22","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"23_CR23","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.H.S.: Controllable text-to-image generation. In: Advances in Neural Information Processing Systems (2019)"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.H.: ManiGAN: text-guided image manipulation. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 7880\u20137889 (2020)","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Object-driven text-to-image synthesis via adversarial training. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 12166\u201312174 (2019)","DOI":"10.1109\/CVPR.2019.01245"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Ma, K., Zhao, B., Sigal, L.: Attribute-guided image generation from layout. In: British Machine Vision Virtual Conference (2020). arXiv:2008.11932","DOI":"10.1109\/CVPR.2019.00878"},{"key":"23_CR27","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv:1411.1784 (2014)"},{"key":"23_CR28","unstructured":"Miyato, T., Koyama, M.: cGANs with projection discriminator. arXiv:1802.05637 (2018)"},{"key":"23_CR29","unstructured":"Nam, S., Kim, Y., Kim, S.J.: Text-adaptive generative adversarial networks: manipulating images with natural language. In: Advances in Neural Information Processing Systems, pp. 42\u201351 (2018)"},{"key":"23_CR30","unstructured":"Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: International Conference on Machine Learning, pp. 2642\u20132651 (2016)"},{"key":"23_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1007\/978-3-030-58539-6_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Pavllo","year":"2020","unstructured":"Pavllo, D., Lucchi, A., Hofmann, T.: Controlling style and semantics in weakly-supervised image generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 482\u2013499. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_29"},{"key":"23_CR32","unstructured":"Ravuri, S., Vinyals, O.: Classification accuracy score for conditional generative models. In: Advances in Neural Information Processing Systems, pp. 12268\u201312279 (2019)"},{"key":"23_CR33","unstructured":"Razavi, A., van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Advances in Neural Information Processing Systems, pp. 14866\u201314876 (2019)"},{"key":"23_CR34","unstructured":"Reed, S.E., 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 (2016)"},{"key":"23_CR35","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, pp. 2234\u20132242 (2016)"},{"key":"23_CR36","unstructured":"Seo, P.H., Lehrmann, A., Han, B., Sigal, L.: Visual reference resolution using attention memory for visual dialog. In: Advances in Neural Information Processing Systems, pp. 3719\u20133729 (2017)"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Sun, W., Wu, T.: Image synthesis from reconfigurable layout and style. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.01063"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Sun, W., Wu, T.: Learning layout and style reconfigurable GANs for controllable image synthesis. arXiv:2003.11571 (2020)","DOI":"10.1109\/TPAMI.2021.3078577"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Sylvain, T., Zhang, P., Bengio, Y., Hjelm, R.D., Sharma, S.: Object-centric image generation from layouts. arXiv:2003.07449 (2020)","DOI":"10.1609\/aaai.v35i3.16368"},{"key":"23_CR40","unstructured":"Theis, L., van den Oord, A., Bethge, M.: A note on the evaluation of generative models. CoRR arXiv:1511.01844 (2015)"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 8798\u20138807 (2017)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Wang, X., Qiao, T., Zhu, J., Hanjalic, A., Scharenborg, O.: S2IGAN: speech-to-image generation via adversarial learning. In: INTERSPEECH (2020)","DOI":"10.21437\/Interspeech.2020-1759"},{"key":"23_CR43","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 Computer Vision and Pattern Recognition, pp. 1316\u20131324 (2017)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"23_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-319-46493-0_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Yan","year":"2016","unstructured":"Yan, X., Yang, J., Sohn, K., Lee, H.: Attribute2Image: conditional image generation from visual attributes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 776\u2013791. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_47"},{"key":"23_CR45","unstructured":"Yikang, L., Ma, T., Bai, Y., Duan, N., Wei, S., Wang, X.: PasteGAN: a semi-parametric method to generate image from scene graph. In: Advances in Neural Information Processing Systems, pp. 3948\u20133958 (2019)"},{"key":"23_CR46","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2017","unstructured":"Zhang, H., et al.: StackGAN++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 41, 1947\u20131962 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, B., Meng, L., Yin, W., Sigal, L.: Image generation from layout. In: Proceedings of the IEEE Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00878"},{"key":"23_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, X., Huang, S., Li, B., Li, Y., Li, J., Zhang, Z.: Text guided person image synthesis. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 3663\u20133672 (2019)","DOI":"10.1109\/CVPR.2019.00378"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"23_CR51","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 Computer Vision and Pattern Recognition, pp. 5802\u20135810 (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92659-5_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T20:28:28Z","timestamp":1674419308000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92659-5_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030926588","9783030926595"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92659-5_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"13 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bonn","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"43","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dagm-gcpr.de\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"116","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":"46","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":"40% - 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":"2.95","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":"4.3","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}