{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:45:01Z","timestamp":1761061501586,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Alibaba-Zhejiang University Joint Institute of Frontier Technologies"},{"name":"MoE Engineering Research Center of Digital Library"},{"name":"the Fundamental Research Funds for the Central Universities."},{"name":"NSFC","award":["62072399, U19B2042"],"award-info":[{"award-number":["62072399, U19B2042"]}]},{"name":"Chinese Knowledge Center for Engineering Sciences and Technology"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475662","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T04:52:26Z","timestamp":1634532746000},"page":"5363-5372","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Similar Scenes Arouse Similar Emotions"],"prefix":"10.1145","author":[{"given":"Guodun","family":"Li","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"given":"Yuchen","family":"Zhai","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"given":"Zehao","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"given":"Yin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1080\/00223980.1940.9917005"},{"volume-title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","year":"2018","author":"Anderson Peter","key":"e_1_3_2_1_2_1"},{"volume-title":"Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization@ACL 2005","year":"2005","author":"Banerjee Satanjeev","key":"e_1_3_2_1_3_1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018151"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_32"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","volume":"1","author":"Devlin Jacob","year":"2019"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0058066"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"volume-title":"Context-dependent memory in two natural environments: On land and underwater. British Journal of psychology","year":"1975","author":"Godden Duncan R","key":"e_1_3_2_1_9_1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350943"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00433"},{"volume-title":"Normalized and Geometry-Aware Self-Attention Network for Image Captioning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","year":"2020","author":"Guo Longteng","key":"e_1_3_2_1_12_1"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2566972.2566993"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"volume-title":"Billion-scale similarity search with GPUs. arXiv preprint arXiv:1702.08734","year":"2017","author":"Johnson Jeff","key":"e_1_3_2_1_15_1"},{"volume-title":"Contextual Word Embeddings and Data Augmentation. CoRR","year":"2021","author":"Katiyar Sulabh","key":"e_1_3_2_1_16_1"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.631"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"volume-title":"UK","year":"2020","author":"Li Xiujun","key":"e_1_3_2_1_20_1"},{"volume-title":"Zurich, Switzerland","year":"2014","author":"Lin Tsung-Yi","key":"e_1_3_2_1_21_1"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01376"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00896"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016387.3016406"},{"volume-title":"Pacific Rim International Conference on Artificial Intelligence. Springer, 270--284","year":"2019","author":"Nezami Omid Mohamad","key":"e_1_3_2_1_25_1"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"volume-title":"Language models are unsupervised multitask learners. OpenAI blog","year":"2019","author":"Radford Alec","key":"e_1_3_2_1_27_1"},{"volume-title":"Liu","year":"2019","author":"Raffel Colin","key":"e_1_3_2_1_28_1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969250"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350972"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01280"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350996"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1322"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3115432"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"volume-title":"Attention-Aware Polarity Sensitive Embedding for Affective Image Retrieval. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","year":"2019","author":"Yao Xingxu","key":"e_1_3_2_1_41_1"},{"volume-title":"Context and Attribute Grounded Dense Captioning. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2019","author":"Yin Guojun","key":"e_1_3_2_1_42_1"},{"volume-title":"Image captioning at will: A versatile scheme for effectively injecting sentiments into image descriptions. arXiv preprint arXiv:1801.10121","year":"2018","author":"You Quanzeng","key":"e_1_3_2_1_43_1"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"volume-title":"VinVL: Making Visual Representations Matter in Vision-Language Models. CoRR","year":"2021","author":"Zhang Pengchuan","key":"e_1_3_2_1_45_1"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414003"},{"volume-title":"MemCap: Memorizing Style Knowledge for Image Captioning. In Thirty-Fourth AAAI conference on artificial intelligence.","year":"2020","author":"Zhao Wentian","key":"e_1_3_2_1_47_1"}],"event":{"name":"MM '21: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Virtual Event China","acronym":"MM '21"},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475662","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:24Z","timestamp":1750193304000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475662"}},"subtitle":["Parallel Data Augmentation for Stylized Image Captioning"],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":47,"alternative-id":["10.1145\/3474085.3475662","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475662","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}