{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T07:40:19Z","timestamp":1765438819445,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811951930"},{"type":"electronic","value":"9789811951947"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-981-19-5194-7_31","type":"book-chapter","created":{"date-parts":[[2022,8,9]],"date-time":"2022-08-09T23:03:17Z","timestamp":1660086197000},"page":"413-424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Unsupervised Style Control for\u00a0Image Captioning"],"prefix":"10.1007","author":[{"given":"Junyu","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhikun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shumin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,10]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"31_CR2","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Chen, T., et al.: \u201cfactual\u201dor \u201cemotional\u201d: stylized image captioning with adaptive learning and attention. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 519\u2013535 (2018)","DOI":"10.1007\/978-3-030-01249-6_32"},{"key":"31_CR4","unstructured":"Dathathri, S., et al.: Plug and play language models: a simple approach to controlled text generation (2019)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Fu, Z., Tan, X., Peng, N., Zhao, D., Yan, R.: Style transfer in text: exploration and evaluation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11330"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Gan, C., Gan, Z., He, X., Gao, J., Deng, L.: Stylenet: generating attractive visual captions with styles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3137\u20133146 (2017)","DOI":"10.1109\/CVPR.2017.108"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Yao, P., Li, J., Lu, H.: MSCap: multi-style image captioning with unpaired stylized text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4204\u20134213 (2019)","DOI":"10.1109\/CVPR.2019.00433"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"31_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"31_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: Dual-level collaborative transformer for image captioning. arXiv preprint arXiv:2101.06462 (2021)","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Mathews, A., Xie, L., He, X.: Semstyle: learning to generate stylised image captions using unaligned text. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00896"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Mathews, A., Xie, L., He, X.: Senticap: generating image descriptions with sentiments. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.10475"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Mathews, A., Xie, L., He, X.: Semstyle: learning to generate stylised image captions using unaligned text. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8591\u20138600 (2018)","DOI":"10.1109\/CVPR.2018.00896"},{"key":"31_CR15","unstructured":"Mokady, R., Hertz, A., Bermano, A.H.: ClipCap: clip prefix for image captioning (2021)"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"31_CR17","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"8","key":"31_CR18","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Jeffrey, W., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"31_CR19","unstructured":"Rakhlin, A.: Convolutional neural networks for sentence classification. GitHub (2016)"},{"issue":"5","key":"31_CR20","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1109\/TMM.2019.2939744","volume":"22","author":"D She","year":"2019","unstructured":"She, D., Yang, J., Cheng, M.-M., Lai, Y.-K., Rosin, P.L., Wang, L.: WSCNet: weakly supervised coupled networks for visual sentiment classification and detection. IEEE Trans. Multimedia 22(5), 1358\u20131371 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"31_CR21","unstructured":"Shen, S., et al.: How much can clip benefit vision-and-language tasks? arXiv preprint arXiv:2107.06383 (2021)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM-an extensible language modeling toolkit. In: Seventh International Conference on Spoken Language Processing (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"31_CR24","unstructured":"Wang, K., Hua, H., Wan, X.: Controllable unsupervised text attribute transfer via editing entangled latent representation. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 684\u2013699 (2018)","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"31_CR26","unstructured":"You, Q., Jin, H., Luo, J.: Image captioning at will: a versatile scheme for effectively injecting sentiments into image descriptions. arXiv preprint arXiv:1801.10121 (2018)"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, S., Ding, G., Huang, Q., Chua, T.-S., Schuller, B.W., Keutzer, K.: Affective image content analysis: a comprehensive survey. In: IJCAI, pp. 5534\u20135541 (2018)","DOI":"10.24963\/ijcai.2018\/780"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, S., et al.: Affective image content analysis: two decades review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. (2021)","DOI":"10.1109\/TPAMI.2021.3094362"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, C., et al.: Exploring contextual word-level style relevance for unsupervised style transfer. arXiv preprint arXiv:2005.02049 (2020)","DOI":"10.18653\/v1\/2020.acl-main.639"}],"container-title":["Communications in Computer and Information Science","Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-19-5194-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:20:35Z","timestamp":1710256835000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-19-5194-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9789811951930","9789811951947"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-19-5194-7_31","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 August 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPCSEE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of Pioneering Computer Scientists, Engineers and Educators","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chengdu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpcsee2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"261","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"65","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}