{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T18:25:12Z","timestamp":1785608712781,"version":"3.56.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T00:00:00Z","timestamp":1675641600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T00:00:00Z","timestamp":1675641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s11263-023-01752-7","type":"journal-article","created":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T09:03:14Z","timestamp":1675674194000},"page":"1073-1090","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Sentimental Visual Captioning using Multimodal Transformer"],"prefix":"10.1007","volume":"131","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2056-6947","authenticated-orcid":false,"given":"Xinxiao","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,6]]},"reference":[{"key":"1752_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., & Zhang, L. (2018). 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).","DOI":"10.1109\/CVPR.2018.00636"},{"key":"1752_CR2","doi-asserted-by":"crossref","unstructured":"Bargal, S. A., Barsoum, E., Ferrer, C. C., & Zhang, C. (2016). Emotion recognition in the wild from videos using images. In Proceedings of the 18th ACM International Conference on Multimodal Interaction (pp 433\u2013436).","DOI":"10.1145\/2993148.2997627"},{"key":"1752_CR3","volume-title":"Natural language processing with Python: Analyzing text with the natural language toolkit","author":"S Bird","year":"2009","unstructured":"Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with Python: Analyzing text with the natural language toolkit. O\u2019Reilly Media, Inc."},{"key":"1752_CR4","doi-asserted-by":"crossref","unstructured":"Borth, D., Ji, R., Chen, T., Breuel, T., & Chang, S. F. (2013). Large-scale visual sentiment ontology and detectors using adjective noun pairs. In ACM MM (pp 223\u2013232).","DOI":"10.1145\/2502081.2502282"},{"key":"1752_CR5","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.imavis.2017.01.011","volume":"65","author":"V Campos","year":"2017","unstructured":"Campos, V., Jou, B., & Giro-i Nieto, X. (2017). From pixels to sentiment: Fine-tuning cnns for visual sentiment prediction. Image and Vision Computing, 65, 15\u201322.","journal-title":"Image and Vision Computing"},{"key":"1752_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C. K., Pan, Z., Liu, M. Y., & Sun, M. (2019). Unsupervised stylish image description generation via domain layer norm. In Proceedings of the AAAI Conference on Artificial Intelligence 33 (pp 8151\u20138158).","DOI":"10.1609\/aaai.v33i01.33018151"},{"key":"1752_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, S., Zhang, W., & Huang, Q. (2018). Less is more: Picking informative frames for video captioning. In Proceedings of the European conference on computer vision (ECCV) (pp 358\u2013373).","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"1752_CR8","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., & Cucchiara, R. (2020). Meshed-memory transformer for image captioning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp 10578\u201310587).","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"1752_CR9","doi-asserted-by":"crossref","unstructured":"Denkowski, M., & Lavie, A. (2014). Meteor universal: Language specific translation evaluation for any target language. In proceedings of the ninth workshop on statistical machine translation (pp 376\u2013380).","DOI":"10.3115\/v1\/W14-3348"},{"key":"1752_CR10","doi-asserted-by":"crossref","unstructured":"Fang, K., Zhou, L., Jin, C., Zhang, Y., Weng, K., Zhang, T., & Fan, W. (2019). Fully convolutional video captioning with coarse-to-fine and inherited attention. In Proceedings of the AAAI Conference on Artificial Intelligence 33 (pp 8271\u20138278).","DOI":"10.1609\/aaai.v33i01.33018271"},{"key":"1752_CR11","doi-asserted-by":"crossref","unstructured":"Gan, C., Gan, Z., He, X., Gao, J., & Deng, L. (2017). Stylenet: Generating attractive visual captions with styles. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp 3137\u20133146).","DOI":"10.1109\/CVPR.2017.108"},{"key":"1752_CR12","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Yao, P., Li, J., & Lu, H. (2019). Mscap: Multi-style image captioning with unpaired stylized text. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp 4204\u20134213).","DOI":"10.1109\/CVPR.2019.00433"},{"key":"1752_CR13","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Zhu, X., Yao, P., Lu, S., & Lu, H. (2020). Normalized and geometry-aware self-attention network for image captioning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp 10327\u201310336).","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"1752_CR14","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., & Satoh, Y. (2018). Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet? In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (pp 6546\u20136555).","DOI":"10.1109\/CVPR.2018.00685"},{"key":"1752_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR) (pp 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1752_CR16","doi-asserted-by":"crossref","unstructured":"Hershey, S., Chaudhuri, S., Ellis, DP., Gemmeke, JF., Jansen, A., Moore, RC., Plakal, M., Platt, D., Saurous, RA., Seybold, B., et\u00a0al. (2017). Cnn architectures for large-scale audio classification. In 2017 ieee international conference on acoustics, speech and signal processing (icassp), IEEE (pp 131\u2013135).","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"1752_CR17","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., & Wei, XY. (2019). Attention on attention for image captioning. In Proceedings of the IEEE International Conference on Computer Vision (pp 4634\u20134643).","DOI":"10.1109\/ICCV.2019.00473"},{"key":"1752_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., & Fei-Fei, L. (2015). Deep visual-semantic alignments for generating image descriptions. In CVPR (pp 3128\u20133137).","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"1752_CR19","unstructured":"Kingma, D. P., Ba, J. (2015). Adam: A method for stochastic optimization. In ICLR."},{"key":"1752_CR20","doi-asserted-by":"crossref","unstructured":"Lei, J., Wang, L., Shen, Y., Yu, D., Berg, TL., & Bansal, M. (2020). Mart: Memory-augmented recurrent transformer for coherent video paragraph captioning. In ACL.","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"1752_CR21","doi-asserted-by":"crossref","unstructured":"Li, G., Zhai, Y., Lin, Z., & Zhang, Y. (2021a). Similar scenes arouse similar emotions: Parallel data augmentation for stylized image captioning. In Proceedings of the 29th ACM International Conference on Multimedia (pp 5363\u20135372).","DOI":"10.1145\/3474085.3475662"},{"key":"1752_CR22","doi-asserted-by":"crossref","unstructured":"Li, T., Hu, Y., & Wu, X. (2021b). Image captioning with inherent sentiment. In 2021 IEEE International Conference on Multimedia and Expo (ICME), IEEE.","DOI":"10.1109\/ICME51207.2021.9428453"},{"key":"1752_CR23","doi-asserted-by":"crossref","unstructured":"Lin, C., Zhao, S., Meng, L., & Chua, TS. (2020). Multi-source domain adaptation for visual sentiment classification. arXiv preprint arXiv:2001.03886.","DOI":"10.1609\/aaai.v34i03.5651"},{"key":"1752_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In European conference on computer vision (pp 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1752_CR25","doi-asserted-by":"crossref","unstructured":"Luo, Y., Ji, J., Sun, X., Cao, L., Wu, Y., Huang, F., Lin, CW., Ji, R. (2021). Dual-level collaborative transformer for image captioning. In Proceedings of the AAAI Conference on Artificial Intelligence (pp 2286\u20132293).","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"1752_CR26","doi-asserted-by":"crossref","unstructured":"Machajdik, J., & Hanbury, A. (2010). Affective image classification using features inspired by psychology and art theory. In ACM MM (pp 83\u201392).","DOI":"10.1145\/1873951.1873965"},{"key":"1752_CR27","doi-asserted-by":"crossref","unstructured":"Mathews, AP., Xie, L., & He, X. (2016). Senticap: Generating image descriptions with sentiments. In Thirtieth AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v30i1.10475"},{"key":"1752_CR28","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.cviu.2018.06.005","volume":"174","author":"D Nguyen","year":"2018","unstructured":"Nguyen, D., Nguyen, K., Sridharan, S., Dean, D., & Fookes, C. (2018). Deep spatio-temporal feature fusion with compact bilinear pooling for multimodal emotion recognition. Computer Vision and Image Understanding, 174, 33\u201342.","journal-title":"Computer Vision and Image Understanding"},{"key":"1752_CR29","doi-asserted-by":"crossref","unstructured":"Pan, B., Cai, H., Huang, D. A., Lee, K. H., Gaidon, A., Adeli, E., & Niebles, J. C. (2020). Spatio-temporal graph for video captioning with knowledge distillation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp 10870\u201310879).","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"1752_CR30","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., & Zhu, W. J. (2002). 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).","DOI":"10.3115\/1073083.1073135"},{"key":"1752_CR31","doi-asserted-by":"crossref","unstructured":"Peng, K. C., Sadovnik, A., Gallagher, A., & Chen, T. (2016). Where do emotions come from? predicting the emotion stimuli map. In ICIP (pp 614\u2013618).","DOI":"10.1109\/ICIP.2016.7532430"},{"issue":"8","key":"1752_CR32","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al. (2019). Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9.","journal-title":"OpenAI blog"},{"key":"1752_CR33","doi-asserted-by":"crossref","unstructured":"Rennie, S. J., Marcheret, E., Mroueh, Y., Ross, J., & Goel, V. (2017). Self-critical sequence training for image captioning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 7008\u20137024).","DOI":"10.1109\/CVPR.2017.131"},{"key":"1752_CR34","doi-asserted-by":"crossref","unstructured":"Stolcke, A., (2002) Srilm-an extensible language modeling toolkit. In Seventh international conference on spoken language processing.","DOI":"10.21437\/ICSLP.2002-303"},{"key":"1752_CR35","doi-asserted-by":"crossref","unstructured":"Suin, M., & Rajagopalan, A. (2020). An efficient framework for dense video captioning. In Proceedings of the AAAI Conference on Artificial Intelligence 34 (pp 12039\u201312046).","DOI":"10.1609\/aaai.v34i07.6881"},{"key":"1752_CR36","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems (pp 5998\u20136008)."},{"key":"1752_CR37","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., & Parikh, D. (2015). Cider: Consensus-based image description evaluation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 4566\u20134575).","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"1752_CR38","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015). Show and tell: A neural image caption generator. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 3156\u20133164).","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"1752_CR39","doi-asserted-by":"crossref","unstructured":"Wang, W., Chen, Z., & Hu, H. (2019). Hierarchical attention network for image captioning. In Proceedings of the AAAI Conference on Artificial Intelligence 33, (pp 8957\u20138964).","DOI":"10.1609\/aaai.v33i01.33018957"},{"issue":"3","key":"1752_CR40","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3), 229\u2013256.","journal-title":"Machine Learning"},{"issue":"9","key":"1752_CR41","doi-asserted-by":"publisher","first-page":"2305","DOI":"10.1007\/s11263-022-01636-2","volume":"130","author":"X Wu","year":"2022","unstructured":"Wu, X., Zhao, W., & Luo, J. (2022). Learning cooperative neural modules for stylized image captioning. International Journal of Computer Vision, 130(9), 2305\u20132320.","journal-title":"International Journal of Computer Vision"},{"key":"1752_CR42","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., & Rui, Y. (2016). Msr-vtt: A large video description dataset for bridging video and language. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 5288\u20135296).","DOI":"10.1109\/CVPR.2016.571"},{"key":"1752_CR43","doi-asserted-by":"crossref","unstructured":"Yang, B., Zou, Y., Liu, F., & Zhang, C. (2021). Non-autoregressive coarse-to-fine video captioning. In Proceedings of the AAAI Conference on Artificial Intelligence 35, (pp 3119\u20133127).","DOI":"10.1609\/aaai.v35i4.16421"},{"key":"1752_CR44","doi-asserted-by":"crossref","unstructured":"Yang, J., She, D., Lai, Y. K., Rosin, P. L., & Yang, M. H. (2018a). Weakly supervised coupled networks for visual sentiment analysis. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 7584\u20137592).","DOI":"10.1109\/CVPR.2018.00791"},{"issue":"9","key":"1752_CR45","doi-asserted-by":"publisher","first-page":"2513","DOI":"10.1109\/TMM.2018.2803520","volume":"20","author":"J Yang","year":"2018","unstructured":"Yang, J., She, D., Sun, M., Cheng, M. M., Rosin, P. L., & Wang, L. (2018). Visual sentiment prediction based on automatic discovery of affective regions. IEEE Transactions on Multimedia, 20(9), 2513\u20132525.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1752_CR46","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., & Courville, A. (2015). Describing videos by exploiting temporal structure. In Proceedings of the IEEE international conference on computer vision (pp 4507\u20134515).","DOI":"10.1109\/ICCV.2015.512"},{"key":"1752_CR47","doi-asserted-by":"crossref","unstructured":"You, Q., Luo, J., Jin, H., & Yang, J. (2015). Robust image sentiment analysis using progressively trained and domain transferred deep networks. In Twenty-ninth AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v29i1.9179"},{"key":"1752_CR48","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., & Luo, J. (2016). Image captioning with semantic attention. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 4651\u20134659).","DOI":"10.1109\/CVPR.2016.503"},{"key":"1752_CR49","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., & Luo, J. (2017). Visual sentiment analysis by attending on local image regions. In Thirty-First AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v31i1.10501"},{"key":"1752_CR50","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., & Xu, W. (2016). Video paragraph captioning using hierarchical recurrent neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 4584\u20134593).","DOI":"10.1109\/CVPR.2016.496"},{"key":"1752_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, P., Li, X., Hu, X., Yang, J., Zhang, L., Wang, L., Choi, Y., Gao, J. (2021). Vinvl: Revisiting visual representations in vision-language models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp 5579\u20135588).","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"1752_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, S., Ma, Y., Gu, Y., Yang, J., Xing, T., Xu, P., Hu, R., Chai, H., & Keutzer, K. (2020). An end-to-end visual-audio attention network for emotion recognition in user-generated videos. In Proceedings of the AAAI Conference on Artificial Intelligence 34 (pp 303\u2013311).","DOI":"10.1609\/aaai.v34i01.5364"},{"key":"1752_CR53","doi-asserted-by":"crossref","unstructured":"Zhao, W., Wu, X., & Zhang, X. (2020). Memcap: Memorizing style knowledge for image captioning. In Proceedings of the AAAI Conference on Artificial Intelligence 34 (pp 12984\u201312992).","DOI":"10.1609\/aaai.v34i07.6998"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01752-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01752-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01752-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T05:09:53Z","timestamp":1677820193000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01752-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,6]]},"references-count":53,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["1752"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01752-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,6]]},"assertion":[{"value":"29 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}