{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T19:53:32Z","timestamp":1759694012257,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"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"}],"funder":[{"DOI":"10.13039\/501100012401","name":"Beijing Science and Technology Planning Project","doi-asserted-by":"publisher","award":["No. Z191100007419001"],"award-info":[{"award-number":["No. Z191100007419001"]}],"id":[{"id":"10.13039\/501100012401","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. U20B2062"],"award-info":[{"award-number":["No. U20B2062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China","award":["No. 61673234"],"award-info":[{"award-number":["No. 61673234"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3479228","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T08:03:42Z","timestamp":1634544222000},"page":"4818-4822","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Semantic Tag Augmented XlanV Model for Video Captioning"],"prefix":"10.1145","author":[{"given":"Yiqing","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Hongwei","family":"Xue","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Jiansheng","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing National Research Center for Information Science and Technology, Beijing, China"}]},{"given":"Huimin","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing, China"}]},{"given":"Hongbing","family":"Ma","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"volume-title":"Proceedings of the 9th workshop on statistical machine translation. 376--380","author":"Michael","key":"e_1_3_2_1_6_1","unstructured":"Michael J. Denkowski and Alon Lavie. 2014. Meteor Universal: Language Specific Translation Evaluation for Any Target Language . In Proceedings of the 9th workshop on statistical machine translation. 376--380 . Michael J. Denkowski and Alon Lavie. 2014. Meteor Universal: Language Specific Translation Evaluation for Any Target Language. In Proceedings of the 9th workshop on statistical machine translation. 376--380."},{"key":"e_1_3_2_1_7_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_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416290"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2969330"},{"key":"e_1_3_2_1_11_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). https:\/\/arxiv.org\/abs\/1412.6980 Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_1_13_1","volume-title":"Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network. arXiv preprint arXiv:2101.11562","author":"Li Yehao","year":"2021","unstructured":"Yehao Li , Yingwei Pan , Ting Yao , Jingwen Chen , and Tao Mei . 2021. Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network. arXiv preprint arXiv:2101.11562 ( 2021 ). Yehao Li, Yingwei Pan, Ting Yao, Jingwen Chen, and Tao Mei. 2021. Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network. arXiv preprint arXiv:2101.11562 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. Text Summarization Branches Out. 1--8.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin . 2004 . Rouge: A package for automatic evaluation of summaries . In Proc. Text Summarization Branches Out. 1--8. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Proc. Text Summarization Branches Out. 1--8."},{"key":"e_1_3_2_1_16_1","volume-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353","author":"Luo Huaishao","year":"2020","unstructured":"Huaishao Luo , Lei Ji , Botian Shi , Haoyang Huang , Nan Duan , Tianrui Li , Jason Li , Taroon Bharti , and Ming Zhou . 2020 . Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020). Huaishao Luo, Lei Ji, Botian Shi, Haoyang Huang, Nan Duan, Tianrui Li, Jason Li, Taroon Bharti, and Ming Zhou. 2020. Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training. arXiv preprint arXiv:2007.02375","author":"Pan Yingwei","year":"2020","unstructured":"Yingwei Pan , Yehao Li , Jianjie Luo , Jun Xu , Ting Yao , and Tao Mei . 2020. Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training. arXiv preprint arXiv:2007.02375 ( 2020 ). Yingwei Pan, Yehao Li, Jianjie Luo, Jun Xu, Ting Yao, and Tao Mei. 2020. Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training. arXiv preprint arXiv:2007.02375 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107702"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_29_1","volume-title":"S3D: single shot multi-span detector via fully 3D convolutional networks. arXiv preprint arXiv:1807.08069","author":"Zhang Da","year":"2018","unstructured":"Da Zhang , Xiyang Dai , Xin Wang , and Yuan-Fang Wang . 2018. S3D: single shot multi-span detector via fully 3D convolutional networks. arXiv preprint arXiv:1807.08069 ( 2018 ). Da Zhang, Xiyang Dai, Xin Wang, and Yuan-Fang Wang. 2018. S3D: single shot multi-span detector via fully 3D convolutional networks. arXiv preprint arXiv:1807.08069 (2018)."}],"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\/3474085.3479228","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3479228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:49Z","timestamp":1750193329000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3479228"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":29,"alternative-id":["10.1145\/3474085.3479228","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3479228","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"}}]}}