{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T01:42:47Z","timestamp":1725586967929},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9206932","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Multi-level Visual Fusion Networks for Image Captioning"],"prefix":"10.1109","author":[{"given":"Dongming","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Canlong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zhiwen","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPR.2017.345"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPR.2018.00754"},{"year":"2015","author":"ranzato","article-title":"Sequence level training with recurrent neural networks","key":"ref12"},{"key":"ref13","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/CVPR.2017.128"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CVPR.2017.131"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"21","article-title":"Gated hierarchical attention for image captioning","author":"wang","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"key":"ref19","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/CVPR.2019.00646"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR.2017.667"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/978-3-030-01216-8_31"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref2","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/CVPR.2018.00636"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref20","first-page":"10685","article-title":"Autoencoding scene graphs for image captioning","author":"yang","year":"2019","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"year":"2017","author":"zhang","article-title":"Actor-critic sequence training for image captioning","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICCV.2017.524"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2019.00859"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2020,7,19]]},"location":"Glasgow, United Kingdom","end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09206932.pdf?arnumber=9206932","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:49:58Z","timestamp":1656452998000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206932\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9206932","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}