{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:22:43Z","timestamp":1750220563473,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T00:00:00Z","timestamp":1614902400000},"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":[[2021,3,5]]},"DOI":"10.1145\/3461353.3461386","type":"proceedings-article","created":{"date-parts":[[2021,9,6]],"date-time":"2021-09-06T17:21:15Z","timestamp":1630948875000},"page":"69-75","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Divided Caption Model with Global Attention"],"prefix":"10.1145","author":[{"given":"Cheng","family":"Yamin","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duan","family":"Hancong","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Zitian","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Zhi","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,9,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Jyoti Aneja Aditya Deshpande and Alexander\u00a0G Schwing. 2018. Convolutional image captioning. (2018) 5561\u20135570.  Jyoti Aneja Aditya Deshpande and Alexander\u00a0G Schwing. 2018. Convolutional image captioning. (2018) 5561\u20135570.","DOI":"10.1109\/CVPR.2018.00583"},{"volume-title":"Sst: Single-stream temporal action proposals.","year":"2017","author":"Buch Shyamal","key":"e_1_3_2_1_2_1"},{"volume-title":"Daps: Deep action proposals for action understanding.","year":"2016","author":"Escorcia Victor","key":"e_1_3_2_1_3_1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305510"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Kenji Hata Frederic Ren Li Fei-Fei and Juan Carlos\u00a0Niebles. 2017. Dense-captioning events in videos. (2017) 706\u2013715.  Ranjay Krishna Kenji Hata Frederic Ren Li Fei-Fei and Juan Carlos\u00a0Niebles. 2017. Dense-captioning events in videos. (2017) 706\u2013715.","DOI":"10.1109\/ICCV.2017.83"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"e_1_3_2_1_9_1","unstructured":"Yingwei Pan Ting Yao Houqiang Li and Tao Mei. 2017. Video captioning with transferred semantic attributes. (2017) 6504\u20136512.  Yingwei Pan Ting Yao Houqiang Li and Tao Mei. 2017. Video captioning with transferred semantic attributes. (2017) 6504\u20136512."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0851-8"},{"volume-title":"Weakly supervised dense video captioning. (2017)","year":"1916","author":"Shen Zhiqiang","key":"e_1_3_2_1_11_1"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Zheng Shou Dongang Wang and Shih-Fu Chang. 2016. Temporal action localization in untrimmed videos via multi-stage cnns. (2016) 1049\u20131058.  Zheng Shou Dongang Wang and Shih-Fu Chang. 2016. Temporal action localization in untrimmed videos via multi-stage cnns. (2016) 1049\u20131058.","DOI":"10.1109\/CVPR.2016.119"},{"volume-title":"A multi-stream bi-directional recurrent neural network for fine-grained action detection. (2016)","year":"1961","author":"Singh Bharat","key":"e_1_3_2_1_13_1"},{"key":"e_1_3_2_1_14_1","unstructured":"Khurram Soomro Amir\u00a0Roshan Zamir and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402(2012).  Khurram Soomro Amir\u00a0Roshan Zamir and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402(2012)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Jingwen Wang Wenhao Jiang Lin Ma Wei Liu and Yong Xu. 2018. Bidirectional attentive fusion with context gating for dense video captioning. (2018) 7190\u20137198.  Jingwen Wang Wenhao Jiang Lin Ma Wei Liu and Yong Xu. 2018. Bidirectional attentive fusion with context gating for dense video captioning. (2018) 7190\u20137198.","DOI":"10.1109\/CVPR.2018.00751"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Limin Wang Wei Li Wen Li and Luc Van\u00a0Gool. 2018. Appearance-and-relation networks for video classification. (2018) 1430\u20131439.  Limin Wang Wei Li Wen Li and Luc Van\u00a0Gool. 2018. Appearance-and-relation networks for video classification. (2018) 1430\u20131439.","DOI":"10.1109\/CVPR.2018.00155"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00048"},{"key":"e_1_3_2_1_20_1","unstructured":"Quanzeng You Hailin Jin Zhaowen Wang Chen Fang and Jiebo Luo. 2016. Image captioning with semantic attention. (2016) 4651\u20134659.  Quanzeng You Hailin Jin Zhaowen Wang Chen Fang and Jiebo Luo. 2016. Image captioning with semantic attention. (2016) 4651\u20134659."},{"key":"e_1_3_2_1_21_1","unstructured":"Haonan Yu Jiang Wang Zhiheng Huang Yi Yang and Wei Xu. 2016. Video paragraph captioning using hierarchical recurrent neural networks. (2016) 4584\u20134593.  Haonan Yu Jiang Wang Zhiheng Huang Yi Yang and Wei Xu. 2016. Video paragraph captioning using hierarchical recurrent neural networks. (2016) 4584\u20134593."},{"key":"e_1_3_2_1_22_1","unstructured":"Dapeng Zhang Feng Xiao Lu Li and Gang Kou. 2019. Learning Spatiotemporal Features of Ride-sourcing Services with Fusion Convolutional Network. arXiv preprint arXiv:1904.06823(2019).  Dapeng Zhang Feng Xiao Lu Li and Gang Kou. 2019. Learning Spatiotemporal Features of Ride-sourcing Services with Fusion Convolutional Network. arXiv preprint arXiv:1904.06823(2019)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Luowei Zhou Chenliang Xu and Jason\u00a0J Corso. 2018. Towards automatic learning of procedures from web instructional videos. (2018).  Luowei Zhou Chenliang Xu and Jason\u00a0J Corso. 2018. Towards automatic learning of procedures from web instructional videos. (2018).","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Luowei Zhou Yingbo Zhou Jason\u00a0J Corso Richard Socher and Caiming Xiong. 2018. End-to-end dense video captioning with masked transformer. (2018) 8739\u20138748.  Luowei Zhou Yingbo Zhou Jason\u00a0J Corso Richard Socher and Caiming Xiong. 2018. End-to-end dense video captioning with masked transformer. (2018) 8739\u20138748.","DOI":"10.1109\/CVPR.2018.00911"}],"event":{"name":"ICIAI 2021: 2021 the 5th International Conference on Innovation in Artificial Intelligence","acronym":"ICIAI 2021","location":"Xia men China"},"container-title":["2021 the 5th International Conference on Innovation in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3461353.3461386","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3461353.3461386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:35Z","timestamp":1750195715000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3461353.3461386"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,5]]},"references-count":24,"alternative-id":["10.1145\/3461353.3461386","10.1145\/3461353"],"URL":"https:\/\/doi.org\/10.1145\/3461353.3461386","relation":{},"subject":[],"published":{"date-parts":[[2021,3,5]]},"assertion":[{"value":"2021-09-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}