{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:41:19Z","timestamp":1755823279699,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871470 and 62106182"],"award-info":[{"award-number":["61871470 and 62106182"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160803"],"award-info":[{"award-number":["2022ZD0160803"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612589","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"4908-4916","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multitask Framework for Graffiti-to-Image Translation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9843-9024","authenticated-orcid":false,"given":"Ying","family":"Yang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4634-3802","authenticated-orcid":false,"given":"Mulin","family":"Chen","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0019-4197","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00484"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01172"},{"key":"e_1_3_2_1_3_1","volume-title":"Proc. ICLR.","author":"Brock Andrew","year":"2019","unstructured":"Andrew Brock, Jeff Donahue, and Karen Simonyan. 2019. Large Scale GAN Training for High Fidelity Natural Image Synthesis. In Proc. ICLR."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137605"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.168"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392386"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00532"},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. NIPS. 8780--8794","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Quinn Nichol. 2021. Diffusion Models Beat GANs on Image Synthesis. In Proc. NIPS. 8780--8794."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"e_1_3_2_1_10_1","unstructured":"Leon A. Gatys Alexander S. Ecker and Matthias Bethge. 2015. A Neural Algorithm of Artistic Style. http:\/\/arxiv.org\/abs\/1508.06576 arXiv preprint arXiv.1508.06576(2015)."},{"volume-title":"Goodfellow et al","year":"2014","key":"e_1_3_2_1_11_1","unstructured":"Ian. Goodfellow et al. 2014. Generative adversarial nets. In Proc. NIPS. 2672--2680."},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. NIPS. 6626--6637","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Proc. NIPS. 6626--6637."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2866771"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01775"},{"volume-title":"Proc. IEEE CVPR. 5967--5976","author":"Isola Phillip","key":"e_1_3_2_1_15_1","unstructured":"Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros. 2017. Image-to-image translation with conditional adversarial networks. In Proc. IEEE CVPR. 5967--5976."},{"volume-title":"Proc. IEEE CVPR. 12341--12351","author":"Wei","key":"e_1_3_2_1_16_1","unstructured":"Wei Ji et al. 2021. Learning Calibrated Medical Image Segmentation via Multi-Rater Agreement Modeling. In Proc. IEEE CVPR. 12341--12351."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"volume-title":"Proc. IEEE CVPR. 105--114","author":"Christian","key":"e_1_3_2_1_18_1","unstructured":"Christian Ledig et al. 2017. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. In Proc. IEEE CVPR. 105--114."},{"volume-title":"Proc","author":"Li Xuelong","key":"e_1_3_2_1_19_1","unstructured":"Xuelong Li, Mulin Chen, Feiping Nie, and Qi Wang. 2017. A Multiview-Based Parameter Free Framework for Group Detection. In Proc. AAAI. AAAI Press, 4147--4153."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3223081"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00557"},{"key":"e_1_3_2_1_22_1","volume-title":"Proc. NIPS. 568--578","author":"Liu Xihui","year":"2019","unstructured":"Xihui Liu, Guojun Yin, Jing Shao, Xiaogang Wang, and Hongsheng Li. 2019. Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis. In Proc. NIPS. 568--578."},{"key":"e_1_3_2_1_23_1","volume-title":"Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation. In ACM International Conference on Multimedia. 1405--1415","author":"Lu Yulei","year":"2022","unstructured":"Yulei Lu, Yawei Luo, Li Zhang, Zheyang Li, Yi Yang, and Jun Xiao. 2022. Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation. In ACM International Conference on Multimedia. 1405--1415."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.740"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01093"},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. ICML. 3478--3487","author":"Mescheder Lars M.","year":"2018","unstructured":"Lars M. Mescheder, Andreas Geiger, and Sebastian Nowozin. 2018. Which Training Methods for GANs do actually Converge. In Proc. ICML. 3478--3487."},{"key":"e_1_3_2_1_27_1","unstructured":"Mehdi Mirza and Simon Osindero. 2014. Conditional Generative Adversarial Nets. (2014). arXiv preprint arXiv:1411.1784(2014)."},{"key":"e_1_3_2_1_28_1","volume-title":"Proc. ICML. 2642--2651","author":"Odena Augustus","year":"2017","unstructured":"Augustus Odena, Christopher Olah, and Jonathon Shlens. 2017. Conditional Image Synthesis with Auxiliary Classifier GANs. In Proc. ICML. 2642--2651."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00918"},{"key":"e_1_3_2_1_31_1","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume":"139","author":"Alec Radford","year":"2021","unstructured":"Alec Radford et al. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proc. ICML, Vol. 139. 8748--8763.","journal-title":"Proc. ICML"},{"key":"e_1_3_2_1_32_1","unstructured":"Sebastian Ruder. 2017. An Overview of Multi-Task Learning in Deep Neural Networks. http:\/\/arxiv.org\/abs\/1706.05098 arXiv preprint arXiv:1706.05098(2017)."},{"key":"e_1_3_2_1_33_1","volume-title":"Proc. ICLR.","author":"Edgar Sch\u00f6","year":"2021","unstructured":"Edgar Sch\u00f6 nfeld, Vadim Sushko, Dan Zhang, Juergen Gall, Bernt Schiele, and Anna Khoreva. 2021. You Only Need Adversarial Supervision for Semantic Image Synthesis. In Proc. ICLR."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01094"},{"key":"e_1_3_2_1_35_1","volume-title":"Proc. ICLR.","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proc. ICLR."},{"key":"e_1_3_2_1_36_1","volume-title":"Multi-caption Text-to-Face Synthesis: Dataset and Algorithm. In ACM International Conference on Multimedia. 2290--2298","author":"Sun Jianxin","year":"2021","unstructured":"Jianxin Sun, Qi Li, Weining Wang, Jian Zhao, and Zhenan Sun. 2021. Multi-caption Text-to-Face Synthesis: Dataset and Algorithm. In ACM International Conference on Multimedia. 2290--2298."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00789"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01379"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"e_1_3_2_1_42_1","unstructured":"Zihao Wang Wei Liu Qian He Xinglong Wu and Zili Yi. 2022. CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP. (2022). arXiv preprint arXiv.2203.00386(2022)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00588"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01779"},{"key":"e_1_3_2_1_46_1","volume-title":"Funkhouser","author":"Yu Fisher","year":"2017","unstructured":"Fisher Yu, Vladlen Koltun, and Thomas A. Funkhouser. 2017. Dilated Residual Networks. In Proc. IEEE CVPR. 636--644."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072883"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"volume-title":"Proc. IEEE ICCV. 2242--2251","author":"Zhu Jun-Yan","key":"e_1_3_2_1_49_1","unstructured":"Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. 2017. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In Proc. IEEE ICCV. 2242--2251."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612589","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:59:24Z","timestamp":1755820764000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612589"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":49,"alternative-id":["10.1145\/3581783.3612589","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612589","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}