{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T10:38:10Z","timestamp":1778495890393,"version":"3.51.4"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"34","license":[{"start":{"date-parts":[[2024,3,6]],"date-time":"2024-03-06T00:00:00Z","timestamp":1709683200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,6]],"date-time":"2024-03-06T00:00:00Z","timestamp":1709683200000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-18748-1","type":"journal-article","created":{"date-parts":[[2024,3,6]],"date-time":"2024-03-06T06:01:55Z","timestamp":1709704915000},"page":"80351-80372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Bimodal sentiment analysis in social media: a one-shot learning approach"],"prefix":"10.1007","volume":"83","author":[{"given":"Zahra","family":"Pakdaman","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0584-6470","authenticated-orcid":false,"given":"Abbas","family":"Koochari","sequence":"additional","affiliation":[]},{"given":"Arash","family":"Sharifi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,6]]},"reference":[{"key":"18748_CR1","doi-asserted-by":"publisher","first-page":"0957","DOI":"10.1016\/j.eswa.2021.115507","volume":"184","author":"K A Ara\u00f1o","year":"2021","unstructured":"Ara\u00f1o K A, Orsenigo C, Soto M, Vercellis C (2021) Multimodal sentiment and emotion recognition in hyperbolic space. Expert Syst Appl 184:0957\u20134174","journal-title":"Expert Syst Appl"},{"key":"18748_CR2","unstructured":"Asakawa T, Aono M (2020) Visual sentiment analysis for few-shot image classification based on metric learning. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Auckland, New Zealand, pp 1081\u20131086"},{"key":"18748_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109409","author":"E Ayetiran","year":"2022","unstructured":"Ayetiran E (2022). Attention-based aspect sentiment classification using enhanced learning through CNN-BiLSTM network. https:\/\/doi.org\/10.1016\/j.knosys.2022.109409","journal-title":"Attention-based aspect sentiment classification using enhanced learning through CNN-BiLSTM network"},{"key":"18748_CR4","doi-asserted-by":"publisher","unstructured":"Hiremath B N, Patil M M (2021) Sarcasm detection using cognitive features of visual data by learning model. Exp Syst With Appl 184:115476. https:\/\/doi.org\/10.1016\/j.eswa.2021.115476","DOI":"10.1016\/j.eswa.2021.115476"},{"key":"18748_CR5","doi-asserted-by":"publisher","unstructured":"Borth D, Ji R, Chen T, Breuel T, Chang S (2013) Large-scale visual sentiment ontology and detectors using adjective noun pairs. In Proceedings of the 21st ACM international conference on multimedia, pp 223\u2013232. https:\/\/doi.org\/10.1145\/2502081.2502282","DOI":"10.1145\/2502081.2502282"},{"key":"18748_CR6","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.neucom.2020.08.019","volume":"417","author":"S Cao","year":"2020","unstructured":"Cao S, An G, Zheng Z, Ruan Q (2020) Interactions guided generative adversarial network for unsupervised image captioning. Neurocomputing 417:419\u2013431","journal-title":"Neurocomputing"},{"key":"18748_CR7","doi-asserted-by":"publisher","unstructured":"Cer D, Yang Y, Kong S, Hua N, Limtiaco N, St. John R, Constant N, Guajardo-Ce \u0301spedes M, Yuan S, Tar C, Sung Y, Strope B, Kurzweil R (2018) Universal sentence encoder. https:\/\/doi.org\/10.48550\/arXiv.1803.11175","DOI":"10.48550\/arXiv.1803.11175"},{"key":"18748_CR8","doi-asserted-by":"publisher","unstructured":"Chen M, Wang S, Liang P, Baltru\u0161aitis T, Zadeh A, Morency L (2018) Multimodal sentiment analysis with word-level fusion and reinforcement learning. In Proceedings of the 19th ACM international conference on multimodal interaction, pp 163\u2013171. https:\/\/doi.org\/10.48550\/arXiv.1802.00924","DOI":"10.48550\/arXiv.1802.00924"},{"key":"18748_CR9","doi-asserted-by":"publisher","unstructured":"Chen T, Zhang Z, You Q, Fang C, Wang Z, Jin H, Luo J (2018) \"Factual\" or \"Emotional\": Stylized image captioning with adaptive learning and attention. https:\/\/doi.org\/10.48550\/arXiv.1807.03871","DOI":"10.48550\/arXiv.1807.03871"},{"key":"18748_CR10","doi-asserted-by":"publisher","unstructured":"Deng C, Ding N, Tan M, Wu Q (2020) Length-controllable image captioning. https:\/\/doi.org\/10.48550\/arXiv.2007.09580","DOI":"10.48550\/arXiv.2007.09580"},{"key":"18748_CR11","unstructured":"Devi P, Shylaja S, Vasist S, Sarnayak S, Hariani R (2020) CAPSTYLE- Stylized image captioning using deep learning models. Kala Sarovar 3(2)"},{"key":"18748_CR12","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformer for language understanding. https:\/\/doi.org\/10.48550\/arXiv.1810.04805","DOI":"10.48550\/arXiv.1810.04805"},{"key":"18748_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.06.011","author":"A Dey","year":"2021","unstructured":"Dey A, Ghosh S, Valveny E, Harit G (2021). Beyond visual semantics: exploring the role of scene text in image understanding. https:\/\/doi.org\/10.1016\/j.patrec.2021.06.011","journal-title":"Beyond visual semantics: exploring the role of scene text in image understanding"},{"key":"18748_CR14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00785","author":"S Fan","year":"2018","unstructured":"Fan S, Shen Z, Jiang M, Koenig B, Xu J, Kankanhalli M, Zhao Q (2018). Emotional attention: A study of image sentiment and visual attention. https:\/\/doi.org\/10.1109\/CVPR.2018.00785","journal-title":"Emotional attention: A study of image sentiment and visual attention"},{"key":"18748_CR15","doi-asserted-by":"publisher","unstructured":"Gan C, Gan Z, He X, Gao J, Deng L (2017) StyleNet: Generating attractive visual captions with styles.\u00a0https:\/\/doi.org\/10.1109\/CVPR.2017.108","DOI":"10.1109\/CVPR.2017.108"},{"key":"18748_CR16","doi-asserted-by":"publisher","unstructured":"Gao T, Yao X, Chen D (2022) SimCSE: Simple contrastive learning of sentence embeddings. https:\/\/doi.org\/10.48550\/arXiv.2104.08821","DOI":"10.48550\/arXiv.2104.08821"},{"key":"18748_CR17","doi-asserted-by":"publisher","unstructured":"Graesser L, Gupta A, Sharma L, Bakhturina E (2017) Sentiment classification using images and label embeddings. https:\/\/doi.org\/10.48550\/arXiv.1712.00725","DOI":"10.48550\/arXiv.1712.00725"},{"key":"18748_CR18","doi-asserted-by":"publisher","unstructured":"Guo L, Liu J, Yao P, Li J, Lu H (2019) MSCap: Multi-style image captioning with unpaired stylized text.\u00a0https:\/\/doi.org\/10.1109\/CVPR.2019.00433","DOI":"10.1109\/CVPR.2019.00433"},{"key":"18748_CR19","doi-asserted-by":"publisher","unstructured":"Hazarika D, Zimmermann R, Poria S (2020) MISA: Modality-invariant and -specific representations for multimodal sentiment analysis. https:\/\/doi.org\/10.1609\/aaai.v34i01.5347","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"18748_CR20","doi-asserted-by":"publisher","unstructured":"Herdade S, Kappeler A, Boakye K, Soares J (2020) Image captioning: transforming object into words.\u00a0https:\/\/doi.org\/10.48550\/arXiv.1906.05963","DOI":"10.48550\/arXiv.1906.05963"},{"key":"18748_CR21","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.knosys.2019.01.019","volume":"167","author":"F Huang","year":"2019","unstructured":"Huang F, Zhang X, Zhao Z, Xu J, Li Z (2019) Image\u2013text sentiment analysis via deep multimodal attentive fusion. Knowl-Based Syst 167:26\u201337","journal-title":"Knowl-Based Syst"},{"key":"18748_CR22","doi-asserted-by":"publisher","unstructured":"Jindal S, Singh S (2015) Image Sentiment analysis using deep convolutional neural networks with domain specific fine tuning. International Conference on Information Processing (ICIP), Pune, India, pp 447\u20132451, IEEE.\u00a0https:\/\/doi.org\/10.1109\/INFOP.2015.7489424","DOI":"10.1109\/INFOP.2015.7489424"},{"key":"18748_CR23","doi-asserted-by":"publisher","unstructured":"Katsurai M, Satoh S (2016) Image sentiment analysis using latent correlations among visual, textual and sentiment views. ICASSP, Shanghai, China, pp 2837\u20132841.\u00a0https:\/\/doi.org\/10.1109\/ICASSP.2016.7472195","DOI":"10.1109\/ICASSP.2016.7472195"},{"key":"18748_CR24","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475692","author":"Z Khan","year":"2021","unstructured":"Khan Z, Fu Y (2021). Exploiting BERT for multimodal target sentiment classification through input space translation. https:\/\/doi.org\/10.1145\/3474085.3475692","journal-title":"Exploiting BERT for multimodal target sentiment classification through input space translation"},{"key":"18748_CR25","unstructured":"Kusner M, Sun Y, Kolkin N, Weinberger K (2015) From word embeddings to document distances. The 32nd International conference on machine learning, Lille, France. JMLR: W&CP, 37:957\u2013966"},{"key":"18748_CR26","doi-asserted-by":"publisher","unstructured":"Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China. In: JMLR Workshop and Conference Proceedings, vol 32. https:\/\/doi.org\/10.48550\/arXiv.1405.4053","DOI":"10.48550\/arXiv.1405.4053"},{"key":"18748_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.021","author":"Y Li","year":"2020","unstructured":"Li Y, Zhang K, Wang J, Gao X (2020). A cognitive brain model for multimodal sentiment analysis based on attention neural networks. https:\/\/doi.org\/10.1016\/j.neucom.2020.10.021","journal-title":"A cognitive brain model for multimodal sentiment analysis based on attention neural networks"},{"key":"18748_CR28","doi-asserted-by":"publisher","unstructured":"Machajdik J, Hanbury A (2010) Affective image classification using features inspired by psychology and art theory. In Proceedings of the 18th ACM international conference on multimedia, pp 83\u201392. https:\/\/doi.org\/10.1145\/1873951.1873965","DOI":"10.1145\/1873951.1873965"},{"key":"18748_CR29","doi-asserted-by":"publisher","unstructured":"Mathews A, Xie L, He X (2015) SentiCap: Generating image descriptions with sentiments. https:\/\/doi.org\/10.48550\/arXiv.1510.01431","DOI":"10.48550\/arXiv.1510.01431"},{"key":"18748_CR30","doi-asserted-by":"publisher","unstructured":"Mittal T, Bhattacharya U, Chandra R, Bera A, Manocha D (2019) M3ER: multiplicative multimodal emotion recognition using facial, textual, and speech cues. In Proceedings of the AAAI conference on artificial intelligence 34(2):1359\u20131367. https:\/\/doi.org\/10.48550\/arXiv.1911.05659","DOI":"10.48550\/arXiv.1911.05659"},{"key":"18748_CR31","doi-asserted-by":"publisher","unstructured":"Nezami O, Dras M, Wan S, Paris C, Hamey L (2019) Towards generating stylized image captions via adversarial training. https:\/\/doi.org\/10.48550\/arXiv.1908.02943","DOI":"10.48550\/arXiv.1908.02943"},{"key":"18748_CR32","doi-asserted-by":"publisher","unstructured":"Nezami O, Dras M, Wan S, Paris C (2018) SENTI-ATTEND: Image captioning using sentiment and attention. https:\/\/doi.org\/10.48550\/arXiv.1811.09789","DOI":"10.48550\/arXiv.1811.09789"},{"key":"18748_CR33","doi-asserted-by":"publisher","unstructured":"Niu T, Zhu S, Pang L, Saddik A (2016) Sentiment analysis on multi-view social data. In International Conference on Multimedia Modeling 15\u201327 https:\/\/doi.org\/10.1007\/978-3-319-27674-8_2","DOI":"10.1007\/978-3-319-27674-8_2"},{"key":"18748_CR34","doi-asserted-by":"crossref","unstructured":"Onita D, Dinu L, Adriana B (2019) From image to text in sentiment analysis via regression and deep learning. Proceedings of Recent Advances in Natural Language Processing, pp 862\u2013868","DOI":"10.26615\/978-954-452-056-4_100"},{"key":"18748_CR35","doi-asserted-by":"publisher","first-page":"2136","DOI":"10.3390\/s21062136","volume":"21","author":"H Ou","year":"2021","unstructured":"Ou H, Qing C, Xu X, Jin J (2021) Multi-level context pyramid network for visual sentiment analysis. Sensors 21:2136. https:\/\/doi.org\/10.3390\/s21062136","journal-title":"Sensors"},{"key":"18748_CR36","doi-asserted-by":"publisher","unstructured":"Pham H, Liang P, Manzini T, Morency L, Poczos B (2018) Found in translation learning robust joint representations by cyclic translations between modalities. In Proceedings of the AAAI conference on artificial intelligence 33(1):6892\u20136899. https:\/\/doi.org\/10.48550\/arXiv.1812.07809","DOI":"10.48550\/arXiv.1812.07809"},{"key":"18748_CR37","doi-asserted-by":"publisher","unstructured":"Learning robust joint representations by cyclic translations between modalities. https:\/\/doi.org\/10.48550\/arXiv.1812.07809","DOI":"10.48550\/arXiv.1812.07809"},{"key":"18748_CR38","doi-asserted-by":"publisher","unstructured":"Rahman W, Hasan Md, Lee S, Zadeh A, Mao C, Morency L, Hoque E (2020) Integrating multimodal information in large pretrained transformers. In Proceedings of the conference. Association for computational linguistics. meeting, 2020:2359. NIH Public Access, https:\/\/doi.org\/10.48550\/arXiv.1908.05787","DOI":"10.48550\/arXiv.1908.05787"},{"key":"18748_CR39","doi-asserted-by":"publisher","unstructured":"Reimers N, Gurevych I (2019) Sentence-BERT: Sentence embeddings using siamese BERT-networks. https:\/\/doi.org\/10.48550\/arXiv.1908.10084","DOI":"10.48550\/arXiv.1908.10084"},{"key":"18748_CR40","doi-asserted-by":"publisher","unstructured":"Shi Z, Zhou X, Qiu X, Zhu X (2020) Improving image captioning with better use of captions. https:\/\/doi.org\/10.48550\/arXiv.2006.11807","DOI":"10.48550\/arXiv.2006.11807"},{"key":"18748_CR41","doi-asserted-by":"crossref","unstructured":"Shin A, Ushiku Y, Harada T (2016) Image captioning with sentiment terms via weakly-supervised sentiment dataset. In BMVC","DOI":"10.5244\/C.30.53"},{"key":"18748_CR42","doi-asserted-by":"publisher","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition, CoRR abs\/1409.1556. https:\/\/doi.org\/10.48550\/arXiv.1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"issue":"27","key":"18748_CR43","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1016\/j.neucom.2018.05.104","volume":"312","author":"K Song","year":"2018","unstructured":"Song K, Yao T, Ling Q, Mei T (2018) Boosting image sentiment analysis with visual attention. Neurocomputing 312(27):218\u2013228","journal-title":"Neurocomputing"},{"key":"18748_CR44","doi-asserted-by":"publisher","unstructured":"Sowmyayani S, Arokia Jensi Rani P(2022) Salient object based visual sentiment analysis by combinig deep features and handcrafted features. https:\/\/doi.org\/10.1007\/s11042-022011982-5","DOI":"10.1007\/s11042-022011982-5"},{"issue":"1","key":"18748_CR45","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1109\/TPAMI.2022.3148210","volume":"45","author":"M Stefanini","year":"2022","unstructured":"Stefanini M, Cornia M, Baraldi L, Cascianelli S, Fiameni G, Cucchiara R (2022) From show to tell: a survey on image captioning. IEEE Trans Pattern Anal Mach Intell 45(1):539\u2013559","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"18748_CR46","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.inffus.2021.07.008","volume":"77","author":"J Sun","year":"2022","unstructured":"Sun J, Lapuschkin S, Samek W, Binder A (2022) Explain and improve: LRP-inference fine-tuning for image captioning models. Inf Fusion 77:233\u2013246. https:\/\/doi.org\/10.1016\/j.inffus.2021.07.008","journal-title":"Inf Fusion"},{"key":"18748_CR47","doi-asserted-by":"publisher","unstructured":"Sung F, Yang Y, Zhang L, Xiang T, Torr P, Hospedales T (2018) Learning to compare: Relation network for few-shot learning. https:\/\/doi.org\/10.48550\/arXiv.1711.06025","DOI":"10.48550\/arXiv.1711.06025"},{"key":"18748_CR48","doi-asserted-by":"publisher","unstructured":"Vadicamo L, Carrara F, Cimino A, Cresci S, Dell\u2019orletta F, Falchi F, Teaconi M (2017) Cross-media learning for image sentiment analysis in the wild. https:\/\/doi.org\/10.1109\/ICCVW.2017.45","DOI":"10.1109\/ICCVW.2017.45"},{"key":"18748_CR49","doi-asserted-by":"publisher","DOI":"10.1007\/11573548_63","author":"S Wang","year":"2005","unstructured":"Wang S, Wang X (2005). Emotion semantics image retrieval: An brief overview. https:\/\/doi.org\/10.1007\/11573548_63","journal-title":"Emotion semantics image retrieval: An brief overview"},{"key":"18748_CR50","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2008.4711705","author":"W Wang","year":"2008","unstructured":"Wang W, He Q (2008). A survey on emotional semantic image retrieval. https:\/\/doi.org\/10.1109\/ICIP.2008.4711705","journal-title":"A survey on emotional semantic image retrieval"},{"key":"18748_CR51","doi-asserted-by":"publisher","unstructured":"Wang Z, Wan Z, Wan X (2020) TransModality: An End2End fusion method with transformer for multimodal sentiment analysis. https:\/\/doi.org\/10.48550\/arXiv.2009.02902","DOI":"10.48550\/arXiv.2009.02902"},{"key":"18748_CR52","first-page":"3534","volume":"4","author":"W Wei-ning","year":"2006","unstructured":"Wei-ning W, Ying-Lin Y, Sheng-ming J (2006) Image Retrieval by emotional semantics: A study of emotional space and feature extraction. IEEE International Conference on Systems, Man and Cybernetics 4:3534\u20133539","journal-title":"IEEE International Conference on Systems, Man and Cybernetics"},{"key":"18748_CR53","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1016\/j.patrec.2021.03.025","volume":"146","author":"H Wen","year":"2021","unstructured":"Wen H, You S, Fu Y (2021) Cross-modal context-gated convolution for multi-modal sentiment analysis. Pattern Recogn Lett 146:252\u2013259","journal-title":"Pattern Recogn Lett"},{"key":"18748_CR54","doi-asserted-by":"crossref","unstructured":"Xu N, Mao W (2017) MultiSentiNet: a deep semantic network for multimodal sentiment analysis. In Proceeding of the 2017 ACM on Conference on Information and Knowledge Management (CIKM\u201917), pp 2399\u20132402","DOI":"10.1145\/3132847.3133142"},{"issue":"1","key":"18748_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3517139","volume":"19","author":"A Yadav","year":"2020","unstructured":"Yadav A, Vishwakarma D (2020) A deep multi-level attentive network for multimodal sentiment analysis. ACM Trans Multimed Comput Commun Appl 19(1):1\u201319","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"18748_CR56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.041","author":"A Yang","year":"2021","unstructured":"Yang A, Shao B, Wu L, Lin X (2021) Multimodal sentiment analysis with unidirectional modality translation. Neurocomputing. https:\/\/doi.org\/10.1016\/j.neucom.2021.09.041","journal-title":"Neurocomputing"},{"key":"18748_CR57","doi-asserted-by":"publisher","first-page":"4014","DOI":"10.1109\/TMM.2020.3035277","volume":"23","author":"X Yang","year":"2021","unstructured":"Yang X, Feng S, Wang D, Zhang Y (2021) Image-text multimodal emotion classification via multi-view attentional network. IEEE Trans Multimedia 23:4014\u20134026. https:\/\/doi.org\/10.1109\/TMM.2020.3035277","journal-title":"IEEE Trans Multimedia"},{"key":"18748_CR58","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-018-1236-4","author":"L Yue","year":"2018","unstructured":"Yue L, Chen W, Li X, Zuo W, Yin M (2018) A survey of sentiment analysis in social media. Knowl Inf Syst. https:\/\/doi.org\/10.1007\/s10115-018-1236-4","journal-title":"Knowl Inf Syst"},{"key":"18748_CR59","doi-asserted-by":"publisher","unstructured":"You Q, Lou J, Jin H, Yang J (2015) Robust image sentiment analysis using progressively trained and domain transferred deep networks, In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI'15) 381\u2013388 https:\/\/doi.org\/10.1609\/aaai.v29i1.9179","DOI":"10.1609\/aaai.v29i1.9179"},{"key":"18748_CR60","doi-asserted-by":"publisher","unstructured":"You Q, Jin H, Luo J (2017) Visual sentiment analysis by attending on local image regions. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) https:\/\/doi.org\/10.1609\/aaai.v31i1.10501","DOI":"10.1609\/aaai.v31i1.10501"},{"key":"18748_CR61","doi-asserted-by":"publisher","unstructured":"You Q, Jin H, Luo J (2018) Image captioning at will: A versatile scheme for effectively injecting sentiments into image descriptions. https:\/\/doi.org\/10.48550\/arXiv.1801.10121","DOI":"10.48550\/arXiv.1801.10121"},{"key":"18748_CR62","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang J (2019) Adapting BERT for targe-oriented multimodal sentiment classification. In Proceedings of the twenty-eighth international joint conference on artificial intelligence, pp 5408\u20135414","DOI":"10.24963\/ijcai.2019\/751"},{"key":"18748_CR63","doi-asserted-by":"crossref","unstructured":"Yu Y, Zhang D, Li S (2022) Unified multi-modal pre-training for few-shot sentiment analysis with prompt-based learning. In Proceeding of the 30th ACM international conference on multimedia. Association for computing machinery, New York, NY, USA, pp 189\u2013198","DOI":"10.1145\/3503161.3548306"},{"key":"18748_CR64","doi-asserted-by":"publisher","unstructured":"Yu Y, Zhang D (2022) Few-shot multi-modal sentiment analysis with prompt-based vision-aware language modeling. IEEE International Conference on Multimedia and Expo (ICME), Taipei, Taiwan, 2022, pp. 1\u20136, https:\/\/doi.org\/10.1109\/ICME52920.2022.9859654","DOI":"10.1109\/ICME52920.2022.9859654"},{"key":"18748_CR65","doi-asserted-by":"crossref","unstructured":"Yuan J, Mcdonough S, You Q, Luo J (2013) Sentribute: image sentiment analysis from a mid-level perspective. In Proceedings of the second international workshop on issues of sentiment discovery and opinion mining,  pp 1\u20138","DOI":"10.1145\/2502069.2502079"},{"key":"18748_CR66","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-022-01556-0","author":"J Yuan","year":"2022","unstructured":"Yuan J, Zhao Y, Qin B (2022). Learning to share masking the non-shared for multi-domain sentiment classification. https:\/\/doi.org\/10.1007\/s13042-022-01556-0","journal-title":"Learning to share masking the non-shared for multi-domain sentiment classification"},{"key":"18748_CR67","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105245","author":"J Zhang","year":"2019","unstructured":"Zhang J, Chen M, Sun H, Li D, Wang Z (2019). Object semantics sentiment correlation analysis enhanced image sentiment classification. https:\/\/doi.org\/10.1016\/j.knosys.2019.105245","journal-title":"Object semantics sentiment correlation analysis enhanced image sentiment classification"},{"key":"18748_CR68","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106803","volume":"216","author":"K Zhang","year":"2021","unstructured":"Zhang K, Zhu Y, Zhang W, Zhu Y (2021) Cross-modal image sentiment analysis via deep correlation of textual semantic. Knowl-Based Syst 216:106803","journal-title":"Knowl-Based Syst"},{"key":"18748_CR69","doi-asserted-by":"publisher","DOI":"10.1016\/2022.070126","author":"T Zhou","year":"2022","unstructured":"Zhou T, Law K, Creighton D (2022). A weakly-supervised graph-based joint sentiment topic model for multi-topic sentiment analysis. https:\/\/doi.org\/10.1016\/2022.070126","journal-title":"A weakly-supervised graph-based joint sentiment topic model for multi-topic sentiment analysis"},{"key":"18748_CR70","doi-asserted-by":"publisher","unstructured":"Zhou Z, Feng H, Qiao B, Wu G, Han D (2023) Syntax-aware hybrid prompt model for few-shot multi-modal sentiment analysis. https:\/\/doi.org\/10.48550\/arXiv.2306.01312","DOI":"10.48550\/arXiv.2306.01312"},{"key":"18748_CR71","doi-asserted-by":"publisher","unstructured":"Zohaib S, Ahmad K, Hicks S, Halvorsen P, Al-Fuqaha A, Conci N, Riegler M (2020) Visual sentiment analysis from disaster images in social media. https:\/\/doi.org\/10.48550\/arXiv.2009.03051","DOI":"10.48550\/arXiv.2009.03051"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18748-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-18748-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18748-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T12:07:30Z","timestamp":1728475650000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-18748-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,6]]},"references-count":71,"journal-issue":{"issue":"34","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["18748"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-18748-1","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,6]]},"assertion":[{"value":"9 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2024","order":4,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}