{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T11:31:31Z","timestamp":1767007891827,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"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":[{"name":"Beijing Natural Science Foundation","award":["4192059"],"award-info":[{"award-number":["4192059"]}]},{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872366,61872364"],"award-info":[{"award-number":["61872366,61872364"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350943","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"765-773","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":80,"title":["Aligning Linguistic Words and Visual Semantic Units for Image Captioning"],"prefix":"10.1145","author":[{"given":"Longteng","family":"Guo","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangwei","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Devices, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Luo","sequence":"additional","affiliation":[{"name":"Huawei Devices, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanqing","family":"Lu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"volume-title":"SPICE: Semantic Propositional Image Caption Evaluation.","year":"2016","author":"Anderson Peter","key":"e_1_3_2_1_1_1"},{"volume-title":"Bottom-up and top-down attention for image captioning and vqa. arXiv preprint arXiv:1707.07998","year":"2017","author":"Anderson Peter","key":"e_1_3_2_1_2_1"},{"volume-title":"Graph convolutional encoders for syntax-aware neural machine translation. arXiv preprint arXiv:1704.04675","year":"2017","author":"Bastings Joost","key":"e_1_3_2_1_3_1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00756"},{"volume-title":"Platt","year":"2014","author":"Fang Hao","key":"e_1_3_2_1_5_1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305512"},{"volume-title":"Stack-captioning: Coarse-to-fine learning for image captioning. arXiv preprint arXiv:1709.03376","year":"2017","author":"Gu Jiuxiang","key":"e_1_3_2_1_7_1"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00433"},{"volume-title":"Deep Residual Learning for Image Recognition. computer vision and pattern recognition","year":"2016","author":"He Kaiming","key":"e_1_3_2_1_9_1"},{"volume-title":"Long short-term memory. Neural computation","year":"1997","author":"Hochreiter Sepp","key":"e_1_3_2_1_10_1"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"volume-title":"Deep visual-semantic alignments for generating image descriptions. computer vision and pattern recognition","year":"2015","author":"Karpathy Andrej","key":"e_1_3_2_1_12_1"},{"volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","year":"2014","author":"Kingma Diederik","key":"e_1_3_2_1_13_1"},{"volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","year":"2016","author":"Kipf Thomas N","key":"e_1_3_2_1_14_1"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"volume-title":"Piotr Dollar, and C Lawrence Zitnick","year":"2014","author":"Lin Tsungyi","key":"e_1_3_2_1_16_1"},{"volume-title":"Context-Aware Visual Policy Network for Sequence-Level Image Captioning. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM, 1416--1424","year":"2018","author":"Liu Daqing","key":"e_1_3_2_1_17_1"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"e_1_3_2_1_21_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 91--99.  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 91--99."},{"volume-title":"Self-critical Sequence Training for Image Captioning. computer vision and pattern recognition","year":"2017","author":"Rennie Steven J","key":"e_1_3_2_1_22_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 1--9.","author":"Teney Damien","key":"e_1_3_2_1_23_1"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"volume-title":"Show and tell: Lessons learned from the 2015 mscoco image captioning challenge","year":"2017","author":"Vinyals Oriol","key":"e_1_3_2_1_25_1"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"volume-title":"Attend and Tell: Neural Image Caption Generation with Visual Attention. international conference on machine learning (2015)","year":"2015","author":"Xu Kelvin","key":"e_1_3_2_1_27_1"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"e_1_3_2_1_30_1","unstructured":"Zhilin Yang Ye Yuan Yuexin Wu Ruslan Salakhutdinov and William W Cohen. 2016. Review Networks for Caption Generation. (2016).  Zhilin Yang Ye Yuan Yuexin Wu Ruslan Salakhutdinov and William W Cohen. 2016. Review Networks for Caption Generation. (2016)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Ting Yao Yingwei Pan Yehao Li Zhaofan Qiu and Tao Mei. 2016. Boosting Image Captioning with Attributes. (2016).  Ting Yao Yingwei Pan Yehao Li Zhaofan Qiu and Tao Mei. 2016. Boosting Image Captioning with Attributes. (2016).","DOI":"10.1109\/ICCV.2017.524"},{"key":"e_1_3_2_1_33_1","unstructured":"Quanzeng You Hailin Jin Zhaowen Wang Chen Fang and Jiebo Luo. 2016. Image Captioning with Semantic Attention. (2016) 4651--4659.  Quanzeng You Hailin Jin Zhaowen Wang Chen Fang and Jiebo Luo. 2016. Image Captioning with Semantic Attention. (2016) 4651--4659."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Nice France","acronym":"MM '19"},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350943","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:17Z","timestamp":1750201997000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350943"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":34,"alternative-id":["10.1145\/3343031.3350943","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350943","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"}}]}}