{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T05:09:06Z","timestamp":1743052146727,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781063"},{"type":"electronic","value":"9783031781070"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78107-0_19","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T19:31:55Z","timestamp":1733081515000},"page":"298-313","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Large Multimodal Models Thrive with\u00a0Little Data for\u00a0Image Emotion Prediction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5846-7956","authenticated-orcid":false,"given":"Peng","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4707-9313","authenticated-orcid":false,"given":"Mohamed","family":"Hussein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8320-8530","authenticated-orcid":false,"given":"Wael Abd","family":"Almageed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Ali, A.R., Shahid, U., Ali, M., Ho, J.: High-level concepts for affective understanding of images. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 679\u2013687. IEEE (2017)","DOI":"10.1109\/WACV.2017.81"},{"key":"19_CR2","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR3","unstructured":"Driess, D., et\u00a0al.: Palm-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Feng, T., Liu, J., Yang, J.: Probing sentiment-oriented pre-training inspired by human sentiment perception mechanism. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2850\u20132860 (2023)","DOI":"10.1109\/CVPR52729.2023.00279"},{"key":"19_CR5","unstructured":"Hartmann, J.: Emotion English distilroberta-base (2022). https:\/\/huggingface.co\/j-hartmann\/emotion-english-distilroberta-base\/"},{"issue":"2","key":"19_CR6","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1002\/mar.4220010206","volume":"1","author":"MB Holbrook","year":"1984","unstructured":"Holbrook, M.B., O\u2019Shaughnessy, J.: The role of emotion in advertising. Psychol. Mark. 1(2), 45\u201364 (1984)","journal-title":"Psychol. Mark."},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Hosseini, M., Caragea, C.: Feature normalization and cartography-based demonstrations for prompt-based fine-tuning on emotion-related tasks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 12881\u201312889 (2023)","DOI":"10.1609\/aaai.v37i11.26514"},{"key":"19_CR8","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"19_CR9","doi-asserted-by":"publisher","unstructured":"Kang, H., Hazarika, D., Kim, D., Kim, J.: Zero-shot visual emotion recognition by exploiting bert. In: Proceedings of SAI Intelligent Systems Conference, pp. 485\u2013494. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-16078-3_33","DOI":"10.1007\/978-3-031-16078-3_33"},{"issue":"11","key":"19_CR10","first-page":"2755","volume":"42","author":"R Kosti","year":"2019","unstructured":"Kosti, R., Alvarez, J.M., Recasens, A., Lapedriza, A.: Context based emotion recognition using emotic dataset. IEEE Trans. Pattern Anal. Mach. Intell. 42(11), 2755\u20132766 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR11","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of the 40th International Conference on Machine Learning. ICML 2023. JMLR.org (2023)"},{"key":"19_CR12","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"19_CR13","doi-asserted-by":"publisher","first-page":"1894","DOI":"10.1109\/TMM.2023.3289762","volume":"26","author":"Y Luo","year":"2023","unstructured":"Luo, Y., Zhong, X., Zeng, M., Xie, J., Wang, S., Liu, G.: Cglf-net: image emotion recognition network by combining global self-attention features and local multiscale features. IEEE Trans. Multimedia 26, 1894\u20131908 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Machajdik, J., Hanbury, A.: Affective image classification using features inspired by psychology and art theory. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 83\u201392 (2010)","DOI":"10.1145\/1873951.1873965"},{"key":"19_CR15","doi-asserted-by":"publisher","first-page":"626","DOI":"10.3758\/BF03192732","volume":"37","author":"JA Mikels","year":"2005","unstructured":"Mikels, J.A., Fredrickson, B.L., Larkin, G.R., Lindberg, C.M., Maglio, S.J., Reuter-Lorenz, P.A.: Emotional category data on images from the international affective picture system. Behav. Res. Methods 37, 626\u2013630 (2005)","journal-title":"Behav. Res. Methods"},{"key":"19_CR16","unstructured":"OpenAI: Gpt-4 technical report. ArXiv arxiv:2303.08774 (2023)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Pan, J., Wang, S.: Progressive visual content understanding network for image emotion classification. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 6034\u20136044 (2023)","DOI":"10.1145\/3581783.3612186"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Panda, R., Zhang, J., Li, H., Lee, J.Y., Lu, X., Roy-Chowdhury, A.K.: Contemplating visual emotions: understanding and overcoming dataset bias. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 579\u2013595 (2018)","DOI":"10.1007\/978-3-030-01216-8_36"},{"key":"19_CR19","volume-title":"Emotions in Social Psychology: Essential Readings","author":"WG Parrott","year":"2001","unstructured":"Parrott, W.G.: Emotions in Social Psychology: Essential Readings. Psychology press, London (2001)"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Patterson, G., Hays, J.: Sun attribute database: discovering, annotating, and recognizing scene attributes. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2751\u20132758. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Peng, K.C., Chen, T., Sadovnik, A., Gallagher, A.C.: A mixed bag of emotions: model, predict, and transfer emotion distributions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 860\u2013868 (2015)","DOI":"10.1109\/CVPR.2015.7298687"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Peng, K.C., Sadovnik, A., Gallagher, A., Chen, T.: Where do emotions come from? predicting the emotion stimuli map. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 614\u2013618. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7532430"},{"key":"19_CR23","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (2019). https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"19_CR25","first-page":"16857","volume":"33","author":"K Song","year":"2020","unstructured":"Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: Mpnet: masked and permuted pre-training for language understanding. Adv. Neural. Inf. Process. Syst. 33, 16857\u201316867 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR26","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"19_CR27","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Truong, Q.T., Lauw, H.W.: Visual sentiment analysis for review images with item-oriented and user-oriented cnn. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1274\u20131282 (2017)","DOI":"10.1145\/3123266.3123374"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Wang, M., Zhao, Y., Wang, Y., Xu, T., Sun, Y.: Image emotion multi-label classification based on multi-graph learning. Expert Syst. Appl., 120641 (2023)","DOI":"10.1016\/j.eswa.2023.120641"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Wang, X., Jia, J., Yin, J., Cai, L.: Interpretable aesthetic features for affective image classification. In: 2013 IEEE International Conference on Image Processing, pp. 3230\u20133234. IEEE (2013)","DOI":"10.1109\/ICIP.2013.6738665"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Wei, Z., et al.: Learning visual emotion representations from web data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13106\u201313115 (2020)","DOI":"10.1109\/CVPR42600.2020.01312"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Yang, J., She, D., Lai, Y.K., Rosin, P.L., Yang, M.H.: Weakly supervised coupled networks for visual sentiment analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7584\u20137592 (2018)","DOI":"10.1109\/CVPR.2018.00791"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"You, Q., Luo, J., Jin, H., Yang, J.: Building a large scale dataset for image emotion recognition: The fine print and the benchmark. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a030 (2016)","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"19_CR34","doi-asserted-by":"publisher","first-page":"2033","DOI":"10.1109\/TMM.2020.3007352","volume":"23","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Xu, M.: Weakly supervised emotion intensity prediction for recognition of emotions in images. IEEE Trans. Multimedia 23, 2033\u20132044 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yang, D., Bao, S., Cao, L., Fan, S.: Emotion classification on code-mixed text messages via soft prompt tuning. In: Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pp. 596\u2013600. Association for Computational Linguistics, Toronto (2023). https:\/\/aclanthology.org\/2023.wassa-1.57","DOI":"10.18653\/v1\/2023.wassa-1.57"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Vinvl: revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579\u20135588 (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Ding, W., Xu, R., Hu, X.: Visual emotion representation learning via emotion-aware pre-training. In: IJCAI, pp. 1679\u20131685 (2022)","DOI":"10.24963\/ijcai.2022\/234"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78107-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T20:05:14Z","timestamp":1733083514000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78107-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031781063","9783031781070"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78107-0_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}