{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:13:48Z","timestamp":1765008828222,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","funder":[{"name":"2023 Central Guiding Local Science and Technology Development Fund Project","award":["2023ZYDF074"],"award-info":[{"award-number":["2023ZYDF074"]}]},{"name":"the project of the Ministry of Industry and Information Technology High-Quality Development Program","award":["CEIEC-2024-ZM02-0056"],"award-info":[{"award-number":["CEIEC-2024-ZM02-0056"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3771058","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:08:11Z","timestamp":1765008491000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Bi-affine Semantic Fusion Generative Adversarial Networks for Text-to-Image Synthesis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2408-366X","authenticated-orcid":false,"given":"Zhiqiang","family":"Zhang","sequence":"first","affiliation":[{"name":"Southwest University of Science and Technology, Mianyang, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6093-5516","authenticated-orcid":false,"given":"Wenxin","family":"Yu","sequence":"additional","affiliation":[{"name":"Southwest University of Science and Technology, Mianyang, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3892-2727","authenticated-orcid":false,"given":"Xin","family":"Cheng","sequence":"additional","affiliation":[{"name":"Southwest University of Science and Technology, Mianyang, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7531-3743","authenticated-orcid":false,"given":"Yunan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southwest University of Science and Technology, Mianyang, Sichuan, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_1_2_2","series-title":"Lecture Notes in Computer Science","first-page":"162","volume-title":"Pattern Recognition - 27th International Conference, ICPR 2024, Kolkata, India, December 1-5, 2024, Proceedings, Part VI","volume":"15306","author":"Jianyu\u00a0Zhang Yibin\u00a0Liu and@","year":"2024","unstructured":"Yibin\u00a0Liu and@ Jianyu\u00a0Zhang, Li Zhang, Shijian Li, and Gang Pan. 2024. A Framework for Image Synthesis Using Supervised Contrastive Learning. In Pattern Recognition - 27th International Conference, ICPR 2024, Kolkata, India, December 1-5, 2024, Proceedings, Part VI(Lecture Notes in Computer Science, Vol.\u00a015306). 162\u2013176."},{"key":"e_1_3_3_1_3_2","unstructured":"Bingchen\u00a0Liu et al. 2020. TIME: Text and Image Mutual-Translation Adversarial Networks. ArXiv abs\/2005.13192 (2020)."},{"key":"e_1_3_3_1_4_2","first-page":"1597","volume-title":"International conference on machine learning","author":"al. Chen\u00a0Ting et","year":"2020","unstructured":"Chen\u00a0Ting et al.2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597\u20131607."},{"key":"e_1_3_3_1_5_2","unstructured":"Ding\u00a0Ming et al. 2021. Cogview: Mastering text-to-image generation via transformers. Advances in Neural Information Processing Systems 34 (2021) 19822\u201319835."},{"key":"e_1_3_3_1_6_2","unstructured":"Dumoulin\u00a0Vincent et al.2016. A learned representation for artistic style. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1610.07629 (2016)."},{"key":"e_1_3_3_1_7_2","first-page":"9729","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"al. He\u00a0Kaiming et","year":"2020","unstructured":"He\u00a0Kaiming et al.2020. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 9729\u20139738."},{"key":"e_1_3_3_1_8_2","unstructured":"Heusel\u00a0Martin et al.2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_9_2","first-page":"740","volume-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","author":"al. Lin Tsung-Yi et","year":"2014","unstructured":"Lin Tsung-Yi et al.2014. Microsoft coco: Common objects in context. In Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740\u2013755."},{"key":"e_1_3_3_1_10_2","first-page":"18187","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"al. Liao\u00a0Wentong et","year":"2022","unstructured":"Liao\u00a0Wentong et al.2022. Text to image generation with semantic-spatial aware gan. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 18187\u201318196."},{"key":"e_1_3_3_1_11_2","unstructured":"Nichol\u00a0Alex et al. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2112.10741 (2021)."},{"key":"e_1_3_3_1_12_2","first-page":"8821","volume-title":"International Conference on Machine Learning","author":"al Ramesh\u00a0Aditya et","year":"2021","unstructured":"Ramesh\u00a0Aditya et al. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821\u20138831."},{"key":"e_1_3_3_1_13_2","unstructured":"Ramesh\u00a0Aditya et al. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.06125 1 2 (2022) 3."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"e_1_3_3_1_15_2","unstructured":"Salimans\u00a0Tim et al.2016. Improved techniques for training gans. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_3_1_16_2","first-page":"16515","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"al. Tao\u00a0Ming et","year":"2022","unstructured":"Tao\u00a0Ming et al.2022. 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. 16515\u201316525."},{"key":"e_1_3_3_1_17_2","unstructured":"Wah\u00a0Catherine et al.2011. The caltech-ucsd birds-200-2011 dataset. (2011)."},{"key":"e_1_3_3_1_18_2","first-page":"1316","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"al. Xu\u00a0Tao et","year":"2018","unstructured":"Xu\u00a0Tao et al.2018. Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1316\u20131324."},{"key":"e_1_3_3_1_19_2","first-page":"2327","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"al. Yin\u00a0Guojun et","year":"2019","unstructured":"Yin\u00a0Guojun et al.2019. Semantics disentangling for text-to-image generation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2327\u20132336."},{"key":"e_1_3_3_1_20_2","unstructured":"Ye\u00a0Senmao et al.2023. Recurrent affine transformation for text-to-image synthesis. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Zhang\u00a0Han et al.2018. Stackgan++: Realistic image synthesis with stacked generative adversarial networks. IEEE transactions on pattern analysis and machine intelligence 41 8 (2018) 1947\u20131962.","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"e_1_3_3_1_22_2","first-page":"5802","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"al. Zhu\u00a0Minfeng et","year":"2019","unstructured":"Zhu\u00a0Minfeng et al.2019. 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. 5802\u20135810."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32588"},{"key":"e_1_3_3_1_24_2","first-page":"18187","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wentong Liao","year":"2021","unstructured":"Liao Wentong, Hu Kaixuan, Yang Ming-Hsuan, and Rosenhahn Bodo. 2021. Text to image generation with semantic-spatial aware gan. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18187\u201318196."},{"key":"e_1_3_3_1_25_2","first-page":"15747","volume-title":"Advances in Neural Information Processing Systems","author":"Yonglong Tian","year":"2019","unstructured":"Tian Yonglong, Krishnan Dilip, and Isola Phillip. 2019. Contrastive multiview coding. In Advances in Neural Information Processing Systems. 15747\u201315757."}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3771058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:09:06Z","timestamp":1765008546000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3771058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":24,"alternative-id":["10.1145\/3743093.3771058","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3771058","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}