{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:16:46Z","timestamp":1742987806995,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819756148"},{"type":"electronic","value":"9789819756155"}],"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\/978-981-97-5615-5_16","type":"book-chapter","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T13:12:02Z","timestamp":1722604322000},"page":"192-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-to-Image Generation with Multiscale Semantic Context-Aware Generative Adversarial Networks"],"prefix":"10.1007","author":[{"given":"Pei","family":"Dong","sequence":"first","affiliation":[]},{"given":"Lei","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Xiangxu","family":"Meng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,3]]},"reference":[{"key":"16_CR1","unstructured":"Balaji, Y., et al.: eDiffI: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12 m: pushing webscale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"16_CR3","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., et al.: Cogview: Mastering text-to-image generation via transformers. Adv. Neural. Inf. Process. Syst. 34, 19822\u201319835 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR4","first-page":"16890","volume":"35","author":"M Ding","year":"2022","unstructured":"Ding, M., Zheng, W., Hong, W., Tang, J.: CogView2: faster and better text-toimage generation via hierarchical transformers. Adv. Neural. Inf. Process. Syst. 35, 16890\u201316902 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10696\u201310706 (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"H\u00e4rk\u00f6nen, E., Aittala, M., Kynk\u00e4\u00e4nniemi, T., Laine, S., Aila, T., Lehtinen, J.: Disentangling random and cyclic effects in time-lapse sequences (2022)","DOI":"10.1145\/3528223.3530170"},{"key":"16_CR7","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Klambauer, G., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a nash equilibrium. CoRR abs\/1706.08500 (2017). http:\/\/arxiv.org\/abs\/1706.08500"},{"key":"16_CR8","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up gans for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10124\u201310134 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"16_CR10","first-page":"852","volume":"34","author":"T Karras","year":"2021","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. Adv. Neural. Inf. Process. Syst. 34, 852\u2013863 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR11","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, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"16_CR12","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"issue":"1","key":"16_CR13","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR14","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1(2), 3 (2022)"},{"key":"16_CR15","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831 (2021)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"16_CR17","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR18","first-page":"17480","volume":"34","author":"A Sauer","year":"2021","unstructured":"Sauer, A., Chitta, K., M\u00fcller, J., Geiger, A.: Projected gans converge faster. Adv. Neural. Inf. Process. Syst. 34, 17480\u201317492 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR19","unstructured":"Sauer, A., Karras, T., Laine, S., Geiger, A., Aila, T.: StyleGAN-T: unlocking the power of gans for fast large-scale text-to-image synthesis. arXiv preprint arXiv:2301.09515 (2023)"},{"key":"16_CR20","doi-asserted-by":"publisher","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: StyleGAN-XL: scaling Style-GAN to large diverse datasets. In: Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings (2022). https:\/\/doi.org\/10.1145\/3528233.3530738","DOI":"10.1145\/3528233.3530738"},{"key":"16_CR21","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Tao, M., Bao, B.K., Tang, H., Xu, C.: Galip: generative adversarial clips for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14214\u201314223 (2023)","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Tao, M., et al.: DF-GAN: a simple and effective baseline for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16515\u201316525 (2022)","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"16_CR24","doi-asserted-by":"publisher","unstructured":"Wu, C., et al.: N\u00dcWA: visual synthesis pre-training for neural visual world creation. In: European Conference on Computer Vision, pp. 720\u2013736. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19787-1_41","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"16_CR25","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: Towards language-free training for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17907\u201317917 (2022)","DOI":"10.1109\/CVPR52688.2022.01738"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5615-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T11:04:37Z","timestamp":1731150277000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5615-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756148","9789819756155"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5615-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}