{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T05:31:51Z","timestamp":1745559111791,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T00:00:00Z","timestamp":1694304000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T00:00:00Z","timestamp":1694304000000},"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":[[2023,9,10]]},"DOI":"10.1109\/acii59096.2023.10388132","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:56:38Z","timestamp":1705352198000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Emotion-Controllable Impression Utterance Generation for Visual Art"],"prefix":"10.1109","author":[{"given":"Ryo","family":"Ueda","sequence":"first","affiliation":[{"name":"The University of Tokyo,Tokyo,Japan"}]},{"given":"Hiromi","family":"Narimatsu","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories,Kanagawa,Japan"}]},{"given":"Yusuke","family":"Miyao","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Tokyo,Japan"}]},{"given":"Shiro","family":"Kumano","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories,Kanagawa,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199942237.001.0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.15"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2013.2247823"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77619-4_11"},{"issue":"3","key":"ref6","first-page":"39","volume-title":"International affective picture system (IAPS): Technical manual and affective ratings","volume":"1","author":"Lang","year":"1997"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-016-0715-3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01140"},{"key":"ref9","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint arXiv:1504.00325"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25360"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2066"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACII55700.2022.9953880"},{"key":"ref13","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"In International Conference on Learning Representations","author":"Dosovitskiy","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"volume-title":"Language models are unsupervised multitask learners","year":"2019","author":"Radford","key":"ref16"},{"volume-title":"Learning transferable visual models from natural language supervision","year":"2021","author":"Radford","key":"ref17"},{"volume-title":"Clipcap: Clip prefix for image captioning","year":"2021","author":"Mokady","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00512"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01280"},{"volume-title":"Multimodal knowledge alignment with reinforcement learning","year":"2022","author":"Yu","key":"ref21"},{"article-title":"Plug and play language models: A simple approach to controlled text generation","volume-title":"In International Conference on Learning Representations","author":"Dathathri","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-5194-7_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"article-title":"Decoupled weight decay regularization","volume-title":"In International Conference on Learning Representations","author":"Loshchilov","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"article-title":"The curious case of neural text degeneration","volume-title":"In International Conference on Learning Representations","author":"Holtzman","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2117\/psysoc.2020-B004"}],"event":{"name":"2023 11th International Conference on Affective Computing and Intelligent Interaction (ACII)","start":{"date-parts":[[2023,9,10]]},"location":"Cambridge, MA, USA","end":{"date-parts":[[2023,9,13]]}},"container-title":["2023 11th International Conference on Affective Computing and Intelligent Interaction (ACII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388070\/10388074\/10388132.pdf?arnumber=10388132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:53:47Z","timestamp":1705542827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10388132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,10]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/acii59096.2023.10388132","relation":{},"subject":[],"published":{"date-parts":[[2023,9,10]]}}}