{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T16:06:01Z","timestamp":1776096361973,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":36,"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\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772535"],"award-info":[{"award-number":["61772535"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["4192028"],"award-info":[{"award-number":["4192028"]}]},{"name":"National Key Research and Development Plan","award":["2016YFB1001202"],"award-info":[{"award-number":["2016YFB1001202"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350571","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"2236-2244","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Neural Storyboard Artist"],"prefix":"10.1145","author":[{"given":"Shizhe","family":"Chen","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bei","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianlong","family":"Fu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihua","family":"Song","sequence":"additional","affiliation":[{"name":"Microsoft XiaoIce, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pingping","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft XiaoIce, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Qi","sequence":"additional","affiliation":[{"name":"Microsoft XiaoIce, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunting","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Film Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing Film Academy, 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","first-page":"1060","volume-title":"International Conference on Machine Learning","author":"Reed Scott","year":"2016"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127905"},{"key":"e_1_3_2_1_5_1","volume-title":"Storygan: A sequential conditional gan for story visualization","author":"Li Yitong","year":"2019"},{"key":"e_1_3_2_1_6_1","first-page":"2672","volume-title":"Advances in neural information processing systems","author":"Goodfellow Ian","year":"2014"},{"key":"e_1_3_2_1_7_1","first-page":"2234","volume-title":"Advances in neural information processing systems","author":"Salimans Tim","year":"2016"},{"key":"e_1_3_2_1_8_1","volume-title":"Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539","author":"Kiros Ryan","year":"2014"},{"key":"e_1_3_2_1_9_1","unstructured":"Fartash Faghri David J Fleet Jamie Ryan Kiros and Sanja Fidler. Vse  Fartash Faghri David J Fleet Jamie Ryan Kiros and Sanja Fidler. Vse"},{"key":"e_1_3_2_1_10_1","volume-title":"Improving visual-semantic embeddings with hard negatives","year":"2018"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00794"},{"key":"e_1_3_2_1_14_1","volume-title":"Carl Vondrick, Kevin Murphy, and Cordelia Schmid. Videobert: A joint model for video and language representation learning. arXiv preprint arXiv:1904.01766","author":"Sun Chen","year":"2019"},{"key":"e_1_3_2_1_15_1","volume-title":"Explaining embodied cognition results. Topics in cognitive science, 4(4):773--785","author":"Lakoff George","year":"2012"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240587"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325050"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00593"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"e_1_3_2_1_20_1","first-page":"2121","volume-title":"Advances in neural information processing systems","author":"Frome Andrea","year":"2013"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"e_1_3_2_1_23_1","first-page":"1889","volume-title":"Advances in neural information processing systems","author":"Karpathy Andrej","year":"2014"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_25_1","first-page":"1993","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Kim Gunhee","year":"2015"},{"key":"e_1_3_2_1_26_1","first-page":"1233","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Kenneth Huang Ting-Hao","year":"2016"},{"key":"e_1_3_2_1_27_1","volume-title":"Retrieve and refine: Improved sequence generation models for dialogue. arXiv preprint arXiv:1808.04776","author":"Weston Jason","year":"2018"},{"key":"e_1_3_2_1_28_1","first-page":"10052","volume-title":"Advances in Neural Information Processing Systems","author":"Hashimoto Tatsunori B","year":"2018"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00986"},{"key":"e_1_3_2_1_34_1","first-page":"740","volume-title":"European conference on computer vision","author":"Lin Tsung-Yi","year":"2014"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018)","author":"Grave Edouard","year":"2018"}],"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\/3343031.3350571","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:24Z","timestamp":1750202004000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350571"}},"subtitle":["Visualizing Stories with Coherent Image Sequences"],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":36,"alternative-id":["10.1145\/3343031.3350571","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350571","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"}}]}}