{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T03:47:34Z","timestamp":1729655254679,"version":"3.28.0"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/cvpr.2019.01280","type":"proceedings-article","created":{"date-parts":[[2020,1,10]],"date-time":"2020-01-10T02:06:13Z","timestamp":1578621973000},"page":"12508-12518","source":"Crossref","is-referenced-by-count":72,"title":["Engaging Image Captioning via Personality"],"prefix":"10.1109","author":[{"given":"Kurt","family":"Shuster","sequence":"first","affiliation":[]},{"given":"Samuel","family":"Humeau","sequence":"additional","affiliation":[]},{"given":"Hexiang","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Antoine","family":"Bordes","sequence":"additional","affiliation":[]},{"given":"Jason","family":"Weston","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/ICCV.2017.208"},{"year":"2016","author":"nam","article-title":"Dual attention networks for multimodal reasoning and matching","key":"ref38"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1145\/1873951.1874254"},{"year":"2018","author":"mahajan","doi-asserted-by":"crossref","article-title":"Exploring the limits of weakly supervised pretraining","key":"ref32","DOI":"10.1007\/978-3-030-01216-8_12"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/ICCV.2015.301"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/CVPR.2018.00754"},{"year":"2017","author":"mostafazadeh","article-title":"Image-grounded conversations: Multimodal context for natural question and response generation","key":"ref37"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.18653\/v1\/D18-1298"},{"key":"ref35","first-page":"3574","article-title":"Senticap: Generating image descriptions with sentiments","author":"mathews","year":"2016","journal-title":"AAAI"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/CVPR.2018.00896"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.18653\/v1\/D16-1230"},{"key":"ref27","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":"ref29","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref2","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"European Conference on Computer Vision"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1037\/0022-3514.93.5.751"},{"year":"2018","author":"jacques","article-title":"First impressions: A survey on computer vision-based apparent personality trait analysis","key":"ref20"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1007\/978-3-319-47635-3"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1515\/TL.2007.014"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR.2015.7298932"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1007\/978-3-319-92108-2_13"},{"year":"2004","author":"lin","journal-title":"Workshop on Text Summarization Branches Out","article-title":"Rouge: A package for automatic evaluation of summaries","key":"ref26"},{"year":"2014","author":"kiros","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","key":"ref25"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref51","first-page":"1","article-title":"Learning two-branch neural networks for image-text matching tasks","author":"wang","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.18653\/v1\/P18-1205"},{"doi-asserted-by":"publisher","key":"ref57","DOI":"10.1162\/tacl_a_00166"},{"year":"2018","author":"you","article-title":"Image captioning at will: A versatile scheme for effectively injecting sentiments into image descriptions","key":"ref56"},{"year":"2018","author":"yoshida","article-title":"Neural joking machine: Humorous image captioning","key":"ref55"},{"key":"ref54","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"},{"year":"2016","author":"xie","journal-title":"CoRR","article-title":"Aggregated residual transformations for deep neural networks","key":"ref53"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1109\/CVPR.2016.541"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1145\/2783258.2788576"},{"year":"2016","author":"eisenschtat","journal-title":"CoRR","article-title":"Capturing deep correlations with 2-way nets","key":"ref11"},{"key":"ref40","first-page":"1987","article-title":"Automatic image captioning","volume":"3","author":"pan","year":"2004","journal-title":"Multimedia and Expo 2004 ICME '04 2004 IEEE International Conference on"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/CVPR.2018.00419"},{"year":"2017","author":"faghri","article-title":"VSE++: improved visual-semantic embeddings","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/CVPR.2017.108"},{"year":"2017","author":"gu","article-title":"Look, imagine and match: Improving textual-visual cross-modal retrieval with generative models","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CVPR.2018.00380"},{"year":"2015","author":"he","article-title":"Deep residual learning for image recognition","key":"ref17"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1609\/icwsm.v8i1.14578","article-title":"What we instagram: A first analysis of instagram photo content and user types","author":"hu","year":"2014","journal-title":"Eighth International AAAI Conference on Weblogs and Social Media"},{"year":"2016","author":"huang","article-title":"Instance-aware image and sentence matching with selective multimodal LSTM","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICCV.2015.279"},{"year":"2018","author":"anderson","journal-title":"CVPR","article-title":"Bottom-up and top-down attention for image captioning and vqa","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.4135\/9781849200479.n7"},{"year":"2016","author":"bojanowski","article-title":"Enriching word vectors with subword information","key":"ref5"},{"year":"2015","author":"chen","article-title":"Microsoft coco captions: Data collection and evaluation server","key":"ref8"},{"year":"2017","author":"chandrasekaran","article-title":"Punny captions: Witty wordplay in image descriptions","key":"ref7"},{"year":"2015","author":"vendrov","journal-title":"CoRR","article-title":"Order-embeddings of images and language","key":"ref49"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR.2017.121"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1145\/2812802"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1145\/1121241.1121281"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref47","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/CVPR.2017.681"},{"key":"ref41","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02"},{"year":"2014","author":"russakovsky","journal-title":"CoRR","article-title":"Imagenet large scale visual recognition challenge","key":"ref44"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/CVPR.2017.131"}],"event":{"name":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2019,6,15]]},"location":"Long Beach, CA, USA","end":{"date-parts":[[2019,6,20]]}},"container-title":["2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8938205\/8953184\/08954085.pdf?arnumber=8954085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T22:58:32Z","timestamp":1695596312000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8954085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":58,"URL":"http:\/\/dx.doi.org\/10.1109\/cvpr.2019.01280","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}
