{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:52:21Z","timestamp":1742914341762,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781711"},{"type":"electronic","value":"9783031781728"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78172-8_11","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T09:47:49Z","timestamp":1733132869000},"page":"162-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Framework for Image Synthesis Using Supervised Contrastive Learning"],"prefix":"10.1007","author":[{"given":"Yibin","family":"Liu","sequence":"first","affiliation":[]},{"given":"Jianyu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Shijian","family":"Li","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Pan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"11_CR1","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"11_CR2","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20\u201325 June 2009, Miami, Florida, USA, pp. 248\u2013255. IEEE Computer Society (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11_CR3","unstructured":"Goodfellow, I.J., 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 27: Annual Conference on Neural Information Processing Systems 2014, 8\u201313 December 2014, Montreal, Quebec, Canada, pp. 2672\u20132680 (2014). https:\/\/proceedings.neurips.cc\/paper\/2014\/hash\/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html"},{"key":"11_CR4","unstructured":"Grill, J., et al.: Bootstrap Your own latent - a new approach to self-supervised learning. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6\u201312 December 2020, virtual (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/f3ada80d5c4ee70142b17b8192b2958e-Abstract.html"},{"key":"11_CR5","doi-asserted-by":"publisher","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, 13\u201319 June 2020, pp. 9726\u20139735. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00975","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"11_CR6","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 18661\u201318673 (2020)"},{"key":"11_CR7","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"11_CR8","doi-asserted-by":"publisher","unstructured":"Li, W., et al.: Object-driven text-to-image synthesis via adversarial training. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16\u201320 June 2019, pp. 12174\u201312182. Computer Vision Foundation\/IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01245. http:\/\/openaccess.thecvf.com\/content_CVPR_2019\/html\/Li_Object-Driven_Text-To-Image_Synthesis_via_Adversarial_Training_CVPR_2019_paper.html","DOI":"10.1109\/CVPR.2019.01245"},{"key":"11_CR9","doi-asserted-by":"publisher","unstructured":"Liao, W., Hu, K., Yang, M.Y., Rosenhahn, B.: Text to image generation with semantic-spatial aware GAN. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18\u201324 June 2022, pp. 18166\u201318175. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01765","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"11_CR10","unstructured":"Lim, J.H., Ye, J.C.: Geometric GAN. CoRR abs\/1705.02894 (2017). http:\/\/arxiv.org\/abs\/1705.02894"},{"key":"11_CR11","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":"11_CR12","unstructured":"Ma\u0142ki\u0144ski, M., Ma\u0144dziuk, J.: Multi-label contrastive learning for abstract visual reasoning. IEEE Trans. Neural Netw. Learn. Syst. (2022)"},{"key":"11_CR13","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. CoRR abs\/1807.03748 (2018). http:\/\/arxiv.org\/abs\/1807.03748"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: MirrorGAN: learning text-to-image generation by redescription. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1505\u20131514 (2019)","DOI":"10.1109\/CVPR.2019.00160"},{"key":"11_CR15","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"11_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":"11_CR17","doi-asserted-by":"crossref","unstructured":"Ruan, S., et al.: DAE-GAN: dynamic aspect-aware GAN for text-to-image synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13960\u201313969 (2021)","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"11_CR18","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, vol. 29 (2016)"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673\u20132681 (1997). https:\/\/doi.org\/10.1109\/78.650093","DOI":"10.1109\/78.650093"},{"key":"11_CR20","doi-asserted-by":"publisher","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 2818\u20132826. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.308","DOI":"10.1109\/CVPR.2016.308"},{"key":"11_CR21","doi-asserted-by":"publisher","unstructured":"Tao, M., Bao, B., Tang, H., Xu, C.: GALIP: generative adversarial CLIPs for text-to-image synthesis. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, 17\u201324 June 2023, pp. 14214\u201314223. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01366","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Tao, M., Tang, H., Wu, F., Jing, X., Bao, B., Xu, C.: DF-GAN: a simple and effective baseline for text-to-image synthesis. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18\u201324 June 2022, pp. 16494\u201316504. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01602","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"11_CR23","unstructured":"Unterthiner, T., et al.: Coulomb GANs: provably optimal Nash equilibria via potential fields. arXiv preprint arXiv:1708.08819 (2017)"},{"key":"11_CR24","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset. California Institute of Technology (2011)"},{"key":"11_CR25","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":"11_CR26","doi-asserted-by":"publisher","unstructured":"Yang, J., et al.: Unified contrastive learning in image-text-label space. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18\u201324 June 2022, pp. 19141\u201319151. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01857","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"11_CR27","unstructured":"Ye, H., Yang, X., Takac, M., Sunderraman, R., Ji, S.: Improving text-to-image synthesis using contrastive learning. arXiv preprint arXiv:2107.02423 (2021)"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Yin, G., Liu, B., Sheng, L., Yu, N., Wang, X., Shao, J.: Semantics disentangling for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2327\u20132336 (2019)","DOI":"10.1109\/CVPR.2019.00243"},{"key":"11_CR29","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow Twins: self-supervised learning via redundancy reduction. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 12310\u201312320. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/zbontar21a.html"},{"key":"11_CR30","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":"11_CR31","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":"11_CR32","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","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78172-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T10:04:54Z","timestamp":1733133894000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78172-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031781711","9783031781728"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78172-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}