{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:45:25Z","timestamp":1774431925023,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004377","name":"The Hong Kong Polytechnic University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2026,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Chinese poetry has been a cultural carrier of storytelling since ancient Chinese culture. Human poets convey their narratives through poems to connect with their audiences regarding scenes, characters, and related relationships and emotions. Although creative GANs for generating poems, lyrics, and metaphors are gaining popularity in recent years, existing studies rarely consider the feelings and relationships among characters in various scenes. Therefore, we propose an end-to-end approach, namely\n                    <jats:italic>Video-Transformed Persona Poem Generation<\/jats:italic>\n                    (VTPPG). VTPPG emulates the poet\u2019s views and captures four qualities: the character\u2019s actions, the character\u2019s relationships, the character\u2019s emotions, and the scenery\u2019s emotions in the machine-generated Chinese quatrain. Accordingly, we conduct a qualitative analysis to compare VTPPG with state-of-the-art baselines, such as Jiu Ge, in terms of the four qualities: fluency, coherence, and meaning. Our results demonstrate that the video-based VTPPG outperforms the baselines by 8.25%. Furthermore, we conducted an in-depth analysis of drama scenes, such as those from Romance of the Three Kingdoms, under the four key qualities, and invited human poets in our evaluation. As a result, VTPPG demonstrates effective generations of expressive texts from videos, potentially facilitating creative democratisation in diversified multimedia contexts.\n                  <\/jats:p>","DOI":"10.1007\/s12559-026-10556-z","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T07:10:40Z","timestamp":1774422640000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VTPPG: End-to-end Video-Transformed Persona Poem Generation"],"prefix":"10.1007","volume":"18","author":[{"given":"Zhihan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Lok Andy","family":"Tai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lik-Hang","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"10556_CR1","doi-asserted-by":"publisher","unstructured":"James JY. Liu. The Art of Chinese Poetry. 1962. In University of Chicago Press. https:\/\/doi.org\/10.2307\/40117793","DOI":"10.2307\/40117793"},{"key":"10556_CR2","doi-asserted-by":"publisher","unstructured":"Lingxiang Wu, Min Xu, Shengsheng Qian, Jianwei Cui. Image to Modern Chinese Poetry Creation via a Constrained Topic-aware Model. ACM Trans. Multimedia Comput. Commun. Appl. 2020;16, 2|:53-21 pages. https:\/\/doi.org\/10.1145\/3381858","DOI":"10.1145\/3381858"},{"issue":"2","key":"10556_CR3","doi-asserted-by":"publisher","first-page":"377","DOI":"10.2307\/2719105","volume":"43","author":"PR Yu","year":"1983","unstructured":"Yu PR. Allegory, allegoresis, and the classic of poetry. Harv J Asiat Stud. 1983;43(2):377\u2013412.","journal-title":"Harv J Asiat Stud"},{"key":"10556_CR4","doi-asserted-by":"publisher","unstructured":"Yizhan Shao, Tong Shao, Minghao Wang, Peng Wang, and Jie Gao. A Sentiment and Style Controllable Approach for Chinese Poetry Generation. In Proceedings of the 30th ACM International Conference on Information amp; Knowledge Management (CIKM \u201921). 2021 https:\/\/doi.org\/10.1145\/3459637.3481964","DOI":"10.1145\/3459637.3481964"},{"key":"10556_CR5","doi-asserted-by":"publisher","unstructured":"Association for Computing Machinery, New York, NY, USA, 4784 \u2013 4788. https:\/\/doi.org\/10.1145\/3459637.3481964","DOI":"10.1145\/3459637.3481964"},{"key":"10556_CR6","doi-asserted-by":"publisher","unstructured":"Y. Wang, Y. Wang, Y. Cao, H. Qu, J. Tang and Y. Wu, \u201dExplore Mindfulness Without Deflection: A Data Art Based On The Book Of Songs,\u201d 2021 IEEE VIS Arts Program (VISAP), New Orleans, LA, USA, 2021;73\u201384, https:\/\/doi.org\/10.1109\/VISAP52981.2021.00014.","DOI":"10.1109\/VISAP52981.2021.00014"},{"key":"10556_CR7","doi-asserted-by":"publisher","unstructured":"Z Cai. How to Read Chinese Poetry: A Guided Anthology. In Columbia University Press. 2007 https:\/\/doi.org\/10.1353\/cri.2010.0003","DOI":"10.1353\/cri.2010.0003"},{"key":"10556_CR8","doi-asserted-by":"publisher","unstructured":"Yip W. Chinese poetry, 2nd., revised: an anthology of major modes and genres. Duke University Press; 1997. https:\/\/doi.org\/10.1215\/9780822382096","DOI":"10.1215\/9780822382096"},{"key":"10556_CR9","unstructured":"WC Williams, and E Weinberger. The New Directions Anthology of Classical Chinese Poetry. In New Directions Publishing. 2004 https:\/\/www.ndbooks.com\/book\/the-new-directions-anthology-of-classical-chinese-poetry\/"},{"key":"10556_CR10","doi-asserted-by":"publisher","unstructured":"Xiaolian Li and Bo Zhang. Discussion on Natural Language Processing and AI Poetry. In Proceedings of the 2020 Confer-ence on Artificial Intelligence and Healthcare (CAIH2020). Association for Computing Machinery, New York, NY, USA. 2020;10 \u2013 13. https:\/\/doi.org\/10.1145\/3433996.3433999","DOI":"10.1145\/3433996.3433999"},{"key":"10556_CR11","doi-asserted-by":"publisher","unstructured":"J. Zhao and H. J. Lee, \u201dClassical Chinese Poetry Generation based on Transformer-XL,\u201d 2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI), Shanghai, China, 2021;57\u201361, https:\/\/doi.org\/10.1109\/ICCEAI52939.2021.00011.","DOI":"10.1109\/ICCEAI52939.2021.00011"},{"key":"10556_CR12","doi-asserted-by":"publisher","unstructured":"C. -M. Huang, K. -L. Lu, Y. -Y. Cheng and Y. -C. Peng, \u201dGenerating Chinese Classical Poetry with Quatrain Generation Model (QGM) Using Encoder-Decoder LSTM,\u201d 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA, 2020;5700\u20135702, https:\/\/doi.org\/10.1109\/BigData50022.2020.9378383.","DOI":"10.1109\/BigData50022.2020.9378383"},{"key":"10556_CR13","doi-asserted-by":"publisher","unstructured":"Y. Liu, D. Liu, J. Lv and Y. Sang, \u201dGenerating Chinese Poetry from Images via Concrete and Abstract Information,\u201d 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 2020;1\u20138, https:\/\/doi.org\/10.1109\/IJCNN48605.2020.9206952.","DOI":"10.1109\/IJCNN48605.2020.9206952"},{"key":"10556_CR14","doi-asserted-by":"publisher","unstructured":"D. Liu, Q. Guo, W. Li and J. Lv, \u201dA Multi-Modal Chinese Poetry Generation Model,\u201d 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil. 2018;1\u20138, https:\/\/doi.org\/10.1109\/IJCNN.2018.8489579.","DOI":"10.1109\/IJCNN.2018.8489579"},{"key":"10556_CR15","doi-asserted-by":"publisher","unstructured":"Lixin Liu, Xiaojun Wan, and Zongming Guo. 2018. Images2Poem: Generating Chinese Poetry from Image Streams. In Proceedings of the 26th ACM international conference on Multimedia (MM \u201918). Association for Computing Machinery, New York, NY, USA. 1967 \u2013 1975. https:\/\/doi.org\/10.1145\/3240508.3241910","DOI":"10.1145\/3240508.3241910"},{"key":"10556_CR16","doi-asserted-by":"publisher","unstructured":"C. Toklu, S. . -P. Liou and M. Das. Videoabstract: a hybrid approach to generate semantically meaningful video summaries. 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532), New York, NY, USA, 2000;1333\u20131336 vol.3, https:\/\/doi.org\/10.1109\/ICME.2000.871012.","DOI":"10.1109\/ICME.2000.871012"},{"key":"10556_CR17","unstructured":"YS Lee, YC Wu, and CH Chang. Integrating Web Information to Generate Chinese Video Summaries. In Proceedings of the 17th International Conference on Software Engineering and Knowledge Engineering (SEKE\u20192005). 2005 https:\/\/www.researchgate.net\/publication\/221391015_Integrating_Web_Information_to_Generate_Chinese_Video_Summaries"},{"key":"10556_CR18","doi-asserted-by":"publisher","unstructured":"M. Rohrbach, W. Qiu, I. Titov, S. Thater, M. Pinkal and B. Schiele. Translating Video Content to Natural Language Descriptions,\u201d 2013 IEEE International Conference on Computer Vision, Sydney, NSW, Australia. 2013;433\u2013440, https:\/\/doi.org\/10.1109\/ICCV.2013.61.","DOI":"10.1109\/ICCV.2013.61"},{"key":"10556_CR19","doi-asserted-by":"publisher","unstructured":"Mingzhe Li, Xiuying Chen, Shen Gao, Zhangming Chan, Dongyan Zhao, and Rui Yan. VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles. 2020. ArXiv: 2010.05406. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.752","DOI":"10.18653\/v1\/2020.emnlp-main.752"},{"key":"10556_CR20","doi-asserted-by":"publisher","unstructured":"Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. SlowFast Networks for Video Recognition. In ICCV. 2019;6201\u20136210. https:\/\/doi.org\/10.48550\/arXiv.1812.03982.","DOI":"10.48550\/arXiv.1812.03982"},{"key":"10556_CR21","doi-asserted-by":"publisher","unstructured":"Xiaoyuan Yi, Ruoyu Li, Cheng Yang, Wenhao Li, and Maosong Sun. MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space. In AAAI, 2020;9450\u20139457. https:\/\/doi.org\/10.1609\/aaai.v34i05.6488","DOI":"10.1609\/aaai.v34i05.6488"},{"key":"10556_CR22","unstructured":"Vijay Gupta. Face and Emotion Recognition. 2020. [Online]. Available: https:\/\/github.com\/vjgpt\/Face-and-Emotion-Recognition."},{"key":"10556_CR23","unstructured":"Octavio Arriaga, Matias Valdenegro, and Paul G. Pl\u00f6ger. Real-time Convolutional Neural Networks for Emotion and Gender Classification. 2017;In arXiv preprint arXiv:1710.07557."},{"key":"10556_CR24","doi-asserted-by":"publisher","unstructured":"Schroff F, Kalenichenko D, Philbin J. FaceNet: A unified embedding for face recognition and clustering. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA. 815\u2013823, https:\/\/doi.org\/10.1109\/CVPR.2015.7298682.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"10556_CR25","doi-asserted-by":"publisher","unstructured":"Q. Sun, B. Schiele and M. Fritz. A Domain Based Approach to Social Relation Recognition,\u201d 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA. 2017;435\u2013444, https:\/\/doi.org\/10.1109\/CVPR.2017.54.","DOI":"10.1109\/CVPR.2017.54"},{"key":"10556_CR26","unstructured":"David Hinton. The Selected Poems of Tu Fu. In New Directions Publishing Corporation. 1989 https:\/\/www.commoncrowbooks.com\/pages\/books\/0092462\/david-hinton-trans-tu-fu\/the-selected-poems-of-tu-fu"},{"key":"10556_CR27","unstructured":"Yang-Shawn. Image-sentiment-analysis. [Online]. 2017;Available: https:\/\/github.com\/Yang-Shawn\/image-sentiment-analysis."},{"key":"10556_CR28","unstructured":"Rosca M, Lakshminaravanan B, Warde-Farley D, Mohamed S. Variational Approaches for Auto-Encoding Generative Adversarial Networks. In arXiv 2017;preprint arXiv:1706.04987."},{"key":"10556_CR29","doi-asserted-by":"publisher","unstructured":"Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courvill, A, Bengio Y. Generative Adversarial Nets. Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, Canada. 2014;2:2672\u20132680. https:\/\/doi.org\/10.3156\/JSOFT.29.5_177_2","DOI":"10.3156\/JSOFT.29.5_177_2"},{"key":"10556_CR30","doi-asserted-by":"publisher","unstructured":"Cheng Y, Sun M, X Yi, and Li W. Stylistic Chinese Poetry Generation via Unsupervised Style Disentanglement. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. https:\/\/doi.org\/10.18653\/v1\/D18-1430","DOI":"10.18653\/v1\/D18-1430"},{"key":"10556_CR31","doi-asserted-by":"publisher","unstructured":"Xiaoyuan Yi, Maosong Sun, Ruoyu Li, and Zonghan Yang. Chinese Poetry Generation with a Working Memory Model. In CoRR, 2018, abs\/1809.04306. https:\/\/doi.org\/10.24963\/ijcai.2018\/633","DOI":"10.24963\/ijcai.2018\/633"},{"key":"10556_CR32","doi-asserted-by":"publisher","unstructured":"Wang Z, He W, Wu H, and et al. 2016. Chinese Poetry Generation with Planning-based Neural Network. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1051\u20131060. https:\/\/doi.org\/10.48550\/arXiv.1610.09889","DOI":"10.48550\/arXiv.1610.09889"},{"key":"10556_CR33","unstructured":"Xudong Deng, cnsenti: An Open-Source Python Library for Chinese Text Sentiment Analysis, 2019. url=https:\/\/github.com\/hi-DaDeng\/cnsenti"},{"key":"10556_CR34","unstructured":"XMNLP: Xianming Li. A Lightweight Chinese Natural Language Processing Toolkit, 2018. url=https:\/\/github.com\/SeanLee97\/xmnlp"},{"issue":"2","key":"10556_CR35","first-page":"205","volume":"3","author":"P Yu","year":"1981","unstructured":"Yu P. Metaphor and Chinese poetry. Chinese Literature: Essays, Articles, Reviews (CLEAR). 1981;3(2):205\u201324.","journal-title":"Chinese Literature: Essays, Articles, Reviews (CLEAR)"},{"key":"10556_CR36","doi-asserted-by":"publisher","unstructured":"Wang Q, Luo T, Wang D. Can Machine Generate Traditional Chinese Poetry? A Feigenbaum Test. In: Liu, CL., Hussain, A., Luo, B., Tan, K., Zeng, Y., Zhang, Z. (eds) Advances in Brain Inspired Cognitive Systems. BICS 2016. Lecture Notes in Computer Science, vol 10023. Springer, Cham. 2016. https:\/\/doi.org\/10.1007\/978-3-319-49685-64","DOI":"10.1007\/978-3-319-49685-64"}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-026-10556-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-026-10556-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-026-10556-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T07:10:49Z","timestamp":1774422649000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-026-10556-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,25]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["10556"],"URL":"https:\/\/doi.org\/10.1007\/s12559-026-10556-z","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,25]]},"assertion":[{"value":"1 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"31"}}