{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:21:17Z","timestamp":1750220477099,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":8,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3478548","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T17:45:27Z","timestamp":1634579127000},"page":"2753-2755","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Text2Video"],"prefix":"10.1145","author":[{"given":"Yipeng","family":"Yu","sequence":"first","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zirui","family":"Tu","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longyu","family":"Lu","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Zhan","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixun","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT.","year":"2019","author":"Devlin J.","key":"e_1_3_2_2_1_1"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Jonathan Shen Ruoming Pang etal 2018. Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions. In ICASSP. 4779--4783.  Jonathan Shen Ruoming Pang et al. 2018. Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions. In ICASSP. 4779--4783.","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12297-2_19"},{"key":"e_1_3_2_2_7_1","unstructured":"Yuxuan Wang Daisy Stanton etal 2018. Style tokens: Unsupervised style modeling control and transfer in end-to-end speech synthesis. In ICML. 5180--5189.  Yuxuan Wang Daisy Stanton et al. 2018. Style tokens: Unsupervised style modeling control and transfer in end-to-end speech synthesis. In ICML. 5180--5189."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Yaping Zhang Shuai Nie Wenju Liu Xing Xu Dongxiang Zhang and Heng Tao Shen. 2019. Sequence-to-sequence domain adaptation network for robust text image recognition. In CVPR. 2740--2749.  Yaping Zhang Shuai Nie Wenju Liu Xing Xu Dongxiang Zhang and Heng Tao Shen. 2019. Sequence-to-sequence domain adaptation network for robust text image recognition. In CVPR. 2740--2749.","DOI":"10.1109\/CVPR.2019.00285"}],"event":{"name":"MM '21: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Virtual Event China","acronym":"MM '21"},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3478548","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3478548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:47Z","timestamp":1750193327000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3478548"}},"subtitle":["Automatic Video Generation Based on Text Scripts"],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":8,"alternative-id":["10.1145\/3474085.3478548","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3478548","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}