{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T22:33:32Z","timestamp":1778193212328,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX201700136"],"award-info":[{"award-number":["BX201700136"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Nanshan District Ling-Hang Team Grant","award":["LHTD20170005"],"award-info":[{"award-number":["LHTD20170005"]}]},{"name":"National Natural Science Foundation of China Major Project","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}]},{"name":"National Program on Key Basic Research Project","award":["2015CB352300"],"award-info":[{"award-number":["2015CB352300"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350986","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"1239-1247","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["Cross-Modal Dual Learning for Sentence-to-Video Generation"],"prefix":"10.1145","author":[{"given":"Yue","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitian","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Prediction and Completion of Human Action Sequences. In European Conference on Computer Vision. 374--390","author":"Cai Haoye","year":"2018"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1070"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 248--255","author":"Deng J."},{"key":"e_1_3_2_1_6_1","unstructured":"Xuguang Duan Wenbing Huang Chuang Gan Jingdong Wang Wenwu Zhu and Junzhou Huang. 2018. Weakly Supervised Dense Event Captioning in Videos. In Advances in Neural Information Processing Systems. 3059--3069.  Xuguang Duan Wenbing Huang Chuang Gan Jingdong Wang Wenwu Zhu and Junzhou Huang. 2018. Weakly Supervised Dense Event Captioning in Videos. In Advances in Neural Information Processing Systems. 3059--3069."},{"key":"e_1_3_2_1_7_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_1_8_1","volume-title":"Proceedings of the 32th International Conference on Machine Learning. 1462--1471","author":"Gregor Karol","year":"2015"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_28"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"e_1_3_2_1_14_1","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. (2013). arXiv:1312.6114.  Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. (2013). arXiv:1312.6114."},{"key":"e_1_3_2_1_15_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence.","author":"Li Yitong","year":"2018"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.159"},{"key":"e_1_3_2_1_17_1","volume-title":"Which Training Methods for GANs Do Actually Converge?","author":"Mescheder Lars","year":"2018"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123309"},{"key":"e_1_3_2_1_19_1","unstructured":"Katsunori Ohnishi. 2018. Hierarchical Video Generation from Orthogonal Information : Optical Flow and Texture. (2018). arXiv:1711.09618v2.  Katsunori Ohnishi. 2018. Hierarchical Video Generation from Orthogonal Information : Optical Flow and Texture. (2018). arXiv:1711.09618v2."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127905"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Tingting Qiao Jing Zhang Duanqing Xu and Dacheng Tao. 2019. MirrorGAN: Learning Text-to-image Generation by Redescription. (2019). arXiv:1903.05854.  Tingting Qiao Jing Zhang Duanqing Xu and Dacheng Tao. 2019. MirrorGAN: Learning Text-to-image Generation by Redescription. (2019). arXiv:1903.05854.","DOI":"10.1109\/CVPR.2019.00160"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Radford Alec","year":"2016"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 33th International Conference on Machine Learning. 1060--1069","author":"Reed Scott","year":"2016"},{"key":"e_1_3_2_1_25_1","unstructured":"Tim Salimans Ian Goodfellow Vicki Cheung Alec Radford and Xi Chen. 2016. Improved Techniques for Training GANs. In Advances in Neural Information Processing Systems. 1--10.  Tim Salimans Ian Goodfellow Vicki Cheung Alec Radford and Xi Chen. 2016. Improved Techniques for Training GANs. In Advances in Neural Information Processing Systems. 1--10."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350981"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Simonyan Karen","year":"2015"},{"key":"e_1_3_2_1_29_1","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems. 3104--3112.  Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems. 3104--3112."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Subhashini Venugopalan Huijuan Xu Jeff Donahue Marcus Rohrbach Raymond Mooney and Kate Saenko. 2014. Translating videos to natural language using deep recurrent neural networks. (2014). arXiv:1412.4729.  Subhashini Venugopalan Huijuan Xu Jeff Donahue Marcus Rohrbach Raymond Mooney and Kate Saenko. 2014. Translating videos to natural language using deep recurrent neural networks. (2014). arXiv:1412.4729.","DOI":"10.3115\/v1\/N15-1173"},{"key":"e_1_3_2_1_33_1","unstructured":"Carl Vondrick Hamed Pirsiavash and Antonio Torralba. 2016. Generating videos with scene dynamics. In Advances in Neural Information Processing Systems. 613-- 621.  Carl Vondrick Hamed Pirsiavash and Antonio Torralba. 2016. Generating videos with scene dynamics. In Advances in Neural Information Processing Systems. 613-- 621."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.361"},{"key":"e_1_3_2_1_35_1","unstructured":"Limin Wang Yuanjun Xiong Zhe Wang and Yu Qiao. 2015. Towards Good Practices for Very Deep Two-Stream ConvNets. (2015). arXiv:1507.02159.  Limin Wang Yuanjun Xiong Zhe Wang and Yu Qiao. 2015. Towards Good Practices for Very Deep Two-Stream ConvNets. (2015). arXiv:1507.02159."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"e_1_3_2_1_38_1","volume-title":"Deconvolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.","author":"Zeiler Matthew D","year":"2010"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"e_1_3_2_1_40_1","volume-title":"Realistic Image Synthesis with Stacked Generative Adversarial Networks","author":"Zhang Han","year":"2018"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France","acronym":"MM '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350986","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:18Z","timestamp":1750201998000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350986"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":41,"alternative-id":["10.1145\/3343031.3350986","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350986","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}