{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:54:39Z","timestamp":1777460079118,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,10,1]],"date-time":"2016-10-01T00:00:00Z","timestamp":1475280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Basic Research 973 Program of China","award":["No. 2012CB316400"],"award-info":[{"award-number":["No. 2012CB316400"]}]},{"name":"National Natural Science Foundation of China","award":["Nos. 61532018 61322212 and 61550110505"],"award-info":[{"award-number":["Nos. 61532018 61322212 and 61550110505"]}]},{"name":"Beijing Science And Technology Project","award":["No. D161100001816001"],"award-info":[{"award-number":["No. D161100001816001"]}]},{"name":"Lenovo Outstanding Young Scientists Program"},{"name":"National High Technology Research and Development 863 Program of China","award":["No. 2014AA015202"],"award-info":[{"award-number":["No. 2014AA015202"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1145\/2964284.2984069","type":"proceedings-article","created":{"date-parts":[[2016,9,29]],"date-time":"2016-09-29T19:17:32Z","timestamp":1475176652000},"page":"1107-1110","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Image Captioning with both Object and Scene Information"],"prefix":"10.1145","author":[{"given":"Xiangyang","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhang","family":"Song","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis","family":"Herranz","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaohui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888089.1888092"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_4_1","volume-title":"ICCV","author":"Ji X.","year":"2015"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"e_1_3_2_1_6_1","volume-title":"Aligning where to see and what to tell: image aption with region-based attention and scene factorization. In arXiv:1506.06272","author":"Jun J.","year":"2015"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_8_1","volume-title":"ACL","author":"Kuznetsova P.","year":"2013"},{"key":"e_1_3_2_1_9_1","volume-title":"ICCV","author":"Lebret R.","year":"2015"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_11_1","volume-title":"ICLR","author":"Mao J.","year":"2015"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2097"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24947-6_17"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_16_1","volume-title":"ICLR","author":"Simonyan K.","year":"2015"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_19_1","volume-title":"ICML","author":"Xu K.","year":"2015"},{"key":"e_1_3_2_1_20_1","volume-title":"NIPS","author":"Zhou B.","year":"2014"}],"event":{"name":"MM '16: ACM Multimedia Conference","location":"Amsterdam The Netherlands","acronym":"MM '16","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 24th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2964284.2984069","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2964284.2984069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:40:00Z","timestamp":1750218000000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2964284.2984069"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":20,"alternative-id":["10.1145\/2964284.2984069","10.1145\/2964284"],"URL":"https:\/\/doi.org\/10.1145\/2964284.2984069","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]},"assertion":[{"value":"2016-10-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}