{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:22:19Z","timestamp":1763018539587,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["No.62025603"],"award-info":[{"award-number":["No.62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["No.2019B1515120049"],"award-info":[{"award-number":["No.2019B1515120049"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["No.20720200077, No.20720200090 and No.20720200091"],"award-info":[{"award-number":["No.20720200077, No.20720200090 and No.20720200091"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.U1705262, No.62176222, No.62176223, No.62176226, No.62072386, No.62072387, No.62072389, No.62002305, No.61772443, No.61802324 and No.61702136"],"award-info":[{"award-number":["No.U1705262, No.62176222, No.62176223, No.62176226, No.62072386, No.62072387, No.62072389, No.62002305, No.61772443, No.61802324 and No.61702136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["No.2021J01002"],"award-info":[{"award-number":["No.2021J01002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3547758","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:43:01Z","timestamp":1665416581000},"page":"5045-5054","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Towards Open-Ended Text-to-Face Generation, Combination and Manipulation"],"prefix":"10.1145","author":[{"given":"Jun","family":"Peng","sequence":"first","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Pan","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"He","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Pinterest, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjian","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"FTGAN: A fully-trained generative adversarial networks for text to face generation. arXiv preprint arXiv:1904.05729","author":"Chen Xiang","year":"2019","unstructured":"Xiang Chen , Lingbo Qing , Xiaohai He , Xiaodong Luo , and Yining Xu . 2019 . FTGAN: A fully-trained generative adversarial networks for text to face generation. arXiv preprint arXiv:1904.05729 (2019). Xiang Chen, Lingbo Qing, Xiaohai He, Xiaodong Luo, and Yining Xu. 2019. FTGAN: A fully-trained generative adversarial networks for text to face generation. arXiv preprint arXiv:1904.05729 (2019)."},{"key":"e_1_3_2_2_2_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_3_1","volume-title":"Adversarial feature learning. arXiv preprint arXiv:1605.09782","author":"Donahue Jeff","year":"2016","unstructured":"Jeff Donahue , Philipp Kr\"ahenb \u00fchl , and Trevor Darrell . 2016. Adversarial feature learning. arXiv preprint arXiv:1605.09782 ( 2016 ). Jeff Donahue, Philipp Kr\"ahenb\u00fchl, and Trevor Darrell. 2016. Adversarial feature learning. arXiv preprint arXiv:1605.09782 (2016)."},{"key":"e_1_3_2_2_4_1","volume-title":"Face2text: Collecting an annotated image description corpus for the generation of rich face descriptions. arXiv preprint arXiv:1803.03827","author":"Gatt Albert","year":"2018","unstructured":"Albert Gatt , Marc Tanti , Adrian Muscat , Patrizia Paggio , Reuben A Farrugia , Claudia Borg , Kenneth P Camilleri , Mike Rosner , and Lonneke Van der Plas . 2018. Face2text: Collecting an annotated image description corpus for the generation of rich face descriptions. arXiv preprint arXiv:1803.03827 ( 2018 ). Albert Gatt, Marc Tanti, Adrian Muscat, Patrizia Paggio, Reuben A Farrugia, Claudia Borg, Kenneth P Camilleri, Mike Rosner, and Lonneke Van der Plas. 2018. Face2text: Collecting an annotated image description corpus for the generation of rich face descriptions. arXiv preprint arXiv:1803.03827 (2018)."},{"key":"e_1_3_2_2_5_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow , Jean Pouget-Abadie , Mehdi Mirza , Bing Xu , David Warde-Farley , Sherjil Ozair , Aaron Courville , and Yoshua Bengio . 2014. Generative adversarial nets. Advances in neural information processing systems , Vol. 27 ( 2014 ), 2672--2680. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems, Vol. 27 (2014), 2672--2680."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_6_1","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"e_1_3_2_2_7_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","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. Advances in neural information processing systems , Vol. 30 ( 2017 ). 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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_8_1","volume-title":"TextFace: Text-to-Style Mapping based Face Generation and Manipulation","author":"Hou Xianxu","year":"2022","unstructured":"Xianxu Hou , Xiaokang Zhang , Yudong Li , and Linlin Shen . 2022. TextFace: Text-to-Style Mapping based Face Generation and Manipulation . IEEE Transactions on Multimedia ( 2022 ). Xianxu Hou, Xiaokang Zhang, Yudong Li, and Linlin Shen. 2022. TextFace: Text-to-Style Mapping based Face Generation and Manipulation. IEEE Transactions on Multimedia (2022)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_9_1","DOI":"10.1109\/ICCV48922.2021.01354"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_10_1","DOI":"10.1109\/CVPR.2019.00453"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_11_1","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_2_12_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba . 2015 . Adam : A Method for Stochastic Optimization. CoRR , Vol. abs\/ 1412 .6980 (2015). Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. CoRR, Vol. abs\/1412.6980 (2015)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_13_1","DOI":"10.1109\/CVPR42600.2020.00790"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_14_1","DOI":"10.1145\/3394171.3413777"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_15_1","DOI":"10.1109\/ICCV.2015.425"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_16_1","DOI":"10.1145\/3394171.3414006"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_17_1","DOI":"10.1109\/CVPR42600.2020.01005"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_18_1","DOI":"10.1109\/TIP.2021.3139234"},{"key":"e_1_3_2_2_19_1","volume-title":"Invertibility of convolutional generative networks from partial measurements. NeurIPS","author":"Ma Fangchang","year":"2019","unstructured":"Fangchang Ma , Ulas Ayaz , and Sertac Karaman . 2019. Invertibility of convolutional generative networks from partial measurements. NeurIPS ( 2019 ). Fangchang Ma, Ulas Ayaz, and Sertac Karaman. 2019. Invertibility of convolutional generative networks from partial measurements. NeurIPS (2019)."},{"key":"e_1_3_2_2_20_1","volume-title":"Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero . 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 ( 2014 ). Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_21_1","DOI":"10.1007\/978-3-030-58555-6_10"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_22_1","DOI":"10.1109\/BigMM.2019.00-42"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_23_1","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"e_1_3_2_2_24_1","volume-title":"Knowledge-Driven Generative Adversarial Network for Text-to-Image Synthesis","author":"Peng Jun","year":"2021","unstructured":"Jun Peng , Yiyi Zhou , Xiaoshuai Sun , Liujuan Cao , Yongjian Wu , Feiyue Huang , and Rongrong Ji. 2021. Knowledge-Driven Generative Adversarial Network for Text-to-Image Synthesis . IEEE Transactions on Multimedia ( 2021 ). Jun Peng, Yiyi Zhou, Xiaoshuai Sun, Liujuan Cao, Yongjian Wu, Feiyue Huang, and Rongrong Ji. 2021. Knowledge-Driven Generative Adversarial Network for Text-to-Image Synthesis. IEEE Transactions on Multimedia (2021)."},{"key":"e_1_3_2_2_25_1","volume-title":"Bogdan Raducanu, and Jose M \u00c1lvarez.","author":"Perarnau Guim","year":"2016","unstructured":"Guim Perarnau , Joost Van De Weijer , Bogdan Raducanu, and Jose M \u00c1lvarez. 2016 . Invertible conditional gans for image editing. arXiv preprint arXiv:1611.06355 (2016). Guim Perarnau, Joost Van De Weijer, Bogdan Raducanu, and Jose M \u00c1lvarez. 2016. Invertible conditional gans for image editing. arXiv preprint arXiv:1611.06355 (2016)."},{"key":"e_1_3_2_2_26_1","volume-title":"Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434","author":"Radford Alec","year":"2015","unstructured":"Alec Radford , Luke Metz , and Soumith Chintala . 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 ( 2015 ). Alec Radford, Luke Metz, and Soumith Chintala. 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)."},{"key":"e_1_3_2_2_27_1","volume-title":"Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh , Mikhail Pavlov , Gabriel Goh , Scott Gray , Chelsea Voss , Alec Radford , Mark Chen , and Ilya Sutskever . 2021. Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092 ( 2021 ). Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092 (2021)."},{"key":"e_1_3_2_2_28_1","volume-title":"International Conference on Machine Learning. PMLR, 1060--1069","author":"Reed Scott","year":"2016","unstructured":"Scott Reed , Zeynep Akata , Xinchen Yan , Lajanugen Logeswaran , Bernt Schiele , and Honglak Lee . 2016 . Generative adversarial text to image synthesis . In International Conference on Machine Learning. PMLR, 1060--1069 . Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, and Honglak Lee. 2016. Generative adversarial text to image synthesis. In International Conference on Machine Learning. PMLR, 1060--1069."},{"doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein etal 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 3 (2015) 211--252.  Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 3 (2015) 211--252.","key":"e_1_3_2_2_29_1","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_2_30_1","volume-title":"Improved techniques for training gans. Advances in neural information processing systems","author":"Salimans Tim","year":"2016","unstructured":"Tim Salimans , Ian Goodfellow , Wojciech Zaremba , Vicki Cheung , Alec Radford , and Xi Chen . 2016. Improved techniques for training gans. Advances in neural information processing systems , Vol. 29 ( 2016 ), 2234--2242. Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved techniques for training gans. Advances in neural information processing systems, Vol. 29 (2016), 2234--2242."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_31_1","DOI":"10.1109\/CVPR42600.2020.00926"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_32_1","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the 29th 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 Proceedings of the 29th ACM International Conference on Multimedia. 2290--2298 . Jianxin Sun, Qi Li, Weining Wang, Jian Zhao, and Zhenan Sun. 2021. Multi-caption Text-to-Face Synthesis: Dataset and Algorithm. In Proceedings of the 29th ACM International Conference on Multimedia. 2290--2298."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_34_1","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_2_35_1","volume-title":"Df-gan: Deep fusion generative adversarial networks for text-to-image synthesis","author":"Tao Ming","year":"2020","unstructured":"Ming Tao , Hao Tang , Songsong Wu , Nicu Sebe , Xiao-Yuan Jing , Fei Wu , and Bingkun Bao . 2020 . Df-gan: Deep fusion generative adversarial networks for text-to-image synthesis . IEEE Transactions on Multimedia ( 2020). Ming Tao, Hao Tang, Songsong Wu, Nicu Sebe, Xiao-Yuan Jing, Fei Wu, and Bingkun Bao. 2020. Df-gan: Deep fusion generative adversarial networks for text-to-image synthesis. IEEE Transactions on Multimedia (2020)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_36_1","DOI":"10.1145\/3450626.3459838"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_37_1","DOI":"10.1145\/3474085.3475226"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_38_1","DOI":"10.1109\/WACV48630.2021.00342"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_39_1","DOI":"10.1109\/CVPR46437.2021.01267"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_40_1","DOI":"10.1109\/CVPR46437.2021.00229"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_41_1","DOI":"10.1109\/CVPR.2018.00143"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_42_1","DOI":"10.1109\/CVPR46437.2021.01200"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_43_1","DOI":"10.1109\/ICCV.2017.629"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_44_1","DOI":"10.1145\/3394171.3414017"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_45_1","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_2_46_1","volume-title":"Lia: Latently invertible autoencoder with adversarial learning. ICLR","author":"Zhu Jiapeng","year":"2019","unstructured":"Jiapeng Zhu , Deli Zhao , Bolei Zhou , and Bo Zhang . 2019 b. Lia: Latently invertible autoencoder with adversarial learning. ICLR (2019). Jiapeng Zhu, Deli Zhao, Bolei Zhou, and Bo Zhang. 2019b. Lia: Latently invertible autoencoder with adversarial learning. ICLR (2019)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_47_1","DOI":"10.1109\/CVPR.2019.00595"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '22","name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal"},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547758","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3547758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:40Z","timestamp":1750188640000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547758"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":47,"alternative-id":["10.1145\/3503161.3547758","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3547758","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}