{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:56:49Z","timestamp":1771703809744,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2018AAA0100603"],"award-info":[{"award-number":["2018AAA0100603"]}]},{"name":"Fundamental Research Funds for the Central Universities","award":["2020QNA5024"],"award-info":[{"award-number":["2020QNA5024"]}]},{"name":"National Natural Science Foundation of China","award":["61836002,U1611461,61751209"],"award-info":[{"award-number":["61836002,U1611461,61751209"]}]},{"name":"Zhejiang Natural Science Foundation","award":["LR19F020006"],"award-info":[{"award-number":["LR19F020006"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413939","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:18Z","timestamp":1602505578000},"page":"4079-4087","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Text-Guided Image Inpainting"],"prefix":"10.1145","author":[{"given":"Zijian","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baoxing","family":"Huai","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Yuan","sequence":"additional","affiliation":[{"name":"Huawei Cloud BU, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Synthesizing natural textures. SI3D","author":"Ashikhmin Michael","year":"2001","unstructured":"Michael Ashikhmin . 2001. Synthesizing natural textures. SI3D , Vol. 1 ( 2001 ), 217--226. Michael Ashikhmin. 2001. Synthesizing natural textures. SI3D, Vol. 1 (2001), 217--226."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Coloma Ballester Marcelo Bertalmio Vicent Caselles Guillermo Sapiro and Joan Verdera. 2000. Filling-in by joint interpolation of vector fields and gray levels. (2000).  Coloma Ballester Marcelo Bertalmio Vicent Caselles Guillermo Sapiro and Joan Verdera. 2000. Filling-in by joint interpolation of vector fields and gray levels. (2000).","DOI":"10.1109\/83.935036"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1576246.1531330"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990497"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"e_1_3_2_2_6_1","volume-title":"Simultaneous structure and texture image inpainting","author":"Bertalmio Marcelo","year":"2003","unstructured":"Marcelo Bertalmio , Luminita Vese , Guillermo Sapiro , and Stanley Osher . 2003. Simultaneous structure and texture image inpainting . IEEE transactions on image processing, Vol. 12 , 8 ( 2003 ), 882--889. Marcelo Bertalmio, Luminita Vese, Guillermo Sapiro, and Stanley Osher. 2003. Simultaneous structure and texture image inpainting. IEEE transactions on image processing, Vol. 12, 8 (2003), 882--889."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641084"},{"key":"e_1_3_2_2_8_1","volume-title":"Neural photo editing with introspective adversarial networks. arXiv preprint arXiv:1609.07093","author":"Brock Andrew","year":"2016","unstructured":"Andrew Brock , Theodore Lim , James M Ritchie , and Nick Weston . 2016. Neural photo editing with introspective adversarial networks. arXiv preprint arXiv:1609.07093 ( 2016 ). Andrew Brock, Theodore Lim, James M Ritchie, and Nick Weston. 2016. Neural photo editing with introspective adversarial networks. arXiv preprint arXiv:1609.07093 (2016)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168140"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.833105"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.608"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2021068"},{"key":"e_1_3_2_2_13_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 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. In Advances in neural information processing systems. 2672--2680."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276382"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPhot.2013.6528313"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"e_1_3_2_2_19_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling . 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 ( 2013 ). Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_2_20_1","unstructured":"Guillaume Lample Neil Zeghidour Nicolas Usunier Antoine Bordes Ludovic Denoyer and Marc'Aurelio Ranzato. 2017. Fader networks: Manipulating images by sliding attributes. In Advances in Neural Information Processing Systems. 5967--5976.  Guillaume Lample Neil Zeghidour Nicolas Usunier Antoine Bordes Ludovic Denoyer and Marc'Aurelio Ranzato. 2017. Fader networks: Manipulating images by sliding attributes. In Advances in Neural Information Processing Systems. 5967--5976."},{"key":"e_1_3_2_2_21_1","volume-title":"Weakly-Supervised Video Moment Retrieval via Semantic Completion Network. arXiv preprint arXiv:1911.08199","author":"Lin Zhijie","year":"2019","unstructured":"Zhijie Lin , Zhou Zhao , Zhu Zhang , Qi Wang , and Huasheng Liu . 2019. Weakly-Supervised Video Moment Retrieval via Semantic Completion Network. arXiv preprint arXiv:1911.08199 ( 2019 ). Zhijie Lin, Zhou Zhao, Zhu Zhang, Qi Wang, and Huasheng Liu. 2019. Weakly-Supervised Video Moment Retrieval via Semantic Completion Network. arXiv preprint arXiv:1911.08199 (2019)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"e_1_3_2_2_23_1","volume-title":"NLTK: the natural language toolkit. arXiv preprint cs\/0205028","author":"Loper Edward","year":"2002","unstructured":"Edward Loper and Steven Bird . 2002. NLTK: the natural language toolkit. arXiv preprint cs\/0205028 ( 2002 ). Edward Loper and Steven Bird. 2002. NLTK: the natural language toolkit. arXiv preprint cs\/0205028 (2002)."},{"key":"e_1_3_2_2_24_1","unstructured":"Seonghyeon Nam Yunji Kim and Seon Joo Kim. 2018. Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language. In Advances in Neural Information Processing Systems (NeurIPS) .  Seonghyeon Nam Yunji Kim and Seon Joo Kim. 2018. Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language. In Advances in Neural Information Processing Systems (NeurIPS) ."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_2_26_1","volume-title":"Pixel recurrent neural networks. arXiv preprint arXiv:1601.06759","author":"van den Oord Aaron","year":"2016","unstructured":"Aaron van den Oord , Nal Kalchbrenner , and Koray Kavukcuoglu . 2016. Pixel recurrent neural networks. arXiv preprint arXiv:1601.06759 ( 2016 ). Aaron van den Oord, Nal Kalchbrenner, and Koray Kavukcuoglu. 2016. Pixel recurrent neural networks. arXiv preprint arXiv:1601.06759 (2016)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"e_1_3_2_2_30_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_31_1","volume-title":"Generative adversarial text to image synthesis. arXiv preprint arXiv:1605.05396","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. arXiv preprint arXiv:1605.05396 ( 2016 ). Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, and Honglak Lee. 2016. Generative adversarial text to image synthesis. arXiv preprint arXiv:1605.05396 (2016)."},{"key":"e_1_3_2_2_32_1","volume-title":"Stochastic backpropagation and approximate inference in deep generative models. arXiv preprint arXiv:1401.4082","author":"Rezende Danilo Jimenez","year":"2014","unstructured":"Danilo Jimenez Rezende , Shakir Mohamed , and Daan Wierstra . 2014. Stochastic backpropagation and approximate inference in deep generative models. arXiv preprint arXiv:1401.4082 ( 2014 ). Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. 2014. Stochastic backpropagation and approximate inference in deep generative models. arXiv preprint arXiv:1401.4082 (2014)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_2_34_1","volume-title":"Nonlinear total variation based noise removal algorithms. Physica D: nonlinear phenomena","author":"Rudin Leonid I","year":"1992","unstructured":"Leonid I Rudin , Stanley Osher , and Emad Fatemi . 1992. Nonlinear total variation based noise removal algorithms. Physica D: nonlinear phenomena , Vol. 60 , 1--4 ( 1992 ), 259--268. Leonid I Rudin, Stanley Osher, and Emad Fatemi. 1992. Nonlinear total variation based noise removal algorithms. Physica D: nonlinear phenomena, Vol. 60, 1--4 (1992), 259--268."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073274"},{"key":"e_1_3_2_2_36_1","volume-title":"Why self-attention? a targeted evaluation of neural machine translation architectures. arXiv preprint arXiv:1808.08946","author":"Tang Gongbo","year":"2018","unstructured":"Gongbo Tang , Mathias M\u00fcller , Annette Rios , and Rico Sennrich . 2018. Why self-attention? a targeted evaluation of neural machine translation architectures. arXiv preprint arXiv:1808.08946 ( 2018 ). Gongbo Tang, Mathias M\u00fcller, Annette Rios, and Rico Sennrich. 2018. Why self-attention? a targeted evaluation of neural machine translation architectures. arXiv preprint arXiv:1808.08946 (2018)."},{"key":"e_1_3_2_2_37_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_38_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200--2011 dataset. (2011).  Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200--2011 dataset. (2011)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00599"},{"key":"e_1_3_2_2_40_1","volume-title":"Controllable semantic image inpainting. arXiv preprint arXiv:1806.05953","author":"Xu Jin","year":"2018","unstructured":"Jin Xu and Yee Whye Teh . 2018. Controllable semantic image inpainting. arXiv preprint arXiv:1806.05953 ( 2018 ). Jin Xu and Yee Whye Teh. 2018. Controllable semantic image inpainting. arXiv preprint arXiv:1806.05953 (2018)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240625"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00878"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00166"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00153"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413939","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:32:07Z","timestamp":1750195927000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413939"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":51,"alternative-id":["10.1145\/3394171.3413939","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413939","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}