{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:00:16Z","timestamp":1767322816934,"version":"3.48.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032113160","type":"print"},{"value":"9783032113177","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-11317-7_3","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:57:24Z","timestamp":1767322644000},"page":"29-40","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Seeing Beyond: Unlocking Image Emotion with\u00a0Contextual Depths"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4711-692X","authenticated-orcid":false,"given":"Federico","family":"Cozzi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8908-6485","authenticated-orcid":false,"given":"Andrea","family":"D\u2019Eusanio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5572-0924","authenticated-orcid":false,"given":"Giuseppe","family":"Boccignone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"issue":"8","key":"3_CR1","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1016\/j.tics.2007.06.003","volume":"11","author":"LF Barrett","year":"2007","unstructured":"Barrett, L.F., Lindquist, K.A., Gendron, M.: Language as context for the perception of emotion. Trends Cogn. Sci. 11(8), 327\u2013332 (2007)","journal-title":"Trends Cogn. Sci."},{"key":"3_CR2","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.neulet.2017.07.045","volume":"693","author":"LF Barrett","year":"2019","unstructured":"Barrett, L.F., Satpute, A.B.: Historical pitfalls and new directions in the neuroscience of emotion. Neurosci. Lett. 693, 9\u201318 (2019)","journal-title":"Neurosci. Lett."},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Borth, D., Ji, R., Chen, T., Breuel, T., Chang, S.F.: Large-scale visual sentiment ontology and detectors using adjective noun pairs. In: Proceedings of the 21st ACM international conference on Multimedia, pp. 223\u2013232 (2013)","DOI":"10.1145\/2502081.2502282"},{"issue":"3","key":"3_CR4","first-page":"617","volume":"12","author":"V Campos","year":"2017","unstructured":"Campos, V., Jou, B., Giro-i Nieto, X.: From pixels to affect: a survey on visual sentiment analysis. IEEE Trans. Aff. Comp. 12(3), 617\u2013637 (2017)","journal-title":"IEEE Trans. Aff. Comp."},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: IEEE Conf. Comput. Vis. Pattern Recog, pp. 113\u2013123 (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"3_CR6","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-031-91578-9_17","volume-title":"ECCV 2024 Workshops","author":"A D\u2019Amelio","year":"2025","unstructured":"D\u2019Amelio, A., Lucchi, M., Boccignone, G.: Scanddm: generalised zero-shot neuro-dynamical modelling of goal-directed attention. In: Del Bue, A., Canton, C., Pont-Tuset, J., Tommasi, T. (eds.) ECCV 2024 Workshops, pp. 234\u2013244. Springer Nature Switzerland, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-91578-9_17"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"issue":"4","key":"3_CR9","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1177\/1754073911410740","volume":"3","author":"P Ekman","year":"2011","unstructured":"Ekman, P., Cordaro, D.: What is meant by calling emotions basic. Emot. Rev. 3(4), 364\u2013370 (2011)","journal-title":"Emot. Rev."},{"key":"3_CR10","unstructured":"Gao, G., Li, C., Wang, Y., Chen, S., Li, Y., Tu, G., Zhang, S.: CLIP-emotion: a zero-shot-based facial and scene emotion recognition. In: Proc. ICASSP, pp.\u00a01\u20135 (2023)"},{"key":"3_CR11","unstructured":"Gemini\u00a0Team, G.: Gemini: A family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"3_CR12","unstructured":"Kim, H., et al.: Fine-tuning clip text encoders with two-step paraphrasing. arXiv preprint arXiv:2402.15120 (2024)"},{"key":"3_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"11","key":"3_CR14","first-page":"2755","volume":"42","author":"R Kosti","year":"2020","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 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, S., Kim, S., Park, J., Sohn, K.: Context-aware emotion recognition networks (2019). https:\/\/arxiv.org\/abs\/1908.05913","DOI":"10.1109\/ICCV.2019.01024"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Limami, F., Hdioud, B., Oulad Haj\u00a0Thami, R.: Contextual emotion detection in images using deep learning. Front. Art. Intell. 7(2024) (2024)","DOI":"10.3389\/frai.2024.1386753"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Machajdik, J., Hanbury, A.: Affective image classification using features inspired by psychology and art theory. In: Proc. 18th ACM International Conference on Multimedia, pp. 83\u201392 (2010)","DOI":"10.1145\/1873951.1873965"},{"key":"3_CR18","unstructured":"Niu, T., Zhu, S.J., Pang, L., El-Saddik, A.: Mvsa: a multi-view sentiment analysis dataset. In: Proc. 2016 ACM on Multimedia Companion, pp. 313\u2013318 (2016)"},{"key":"3_CR19","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"3_CR20","unstructured":"Wang, Y., Wang, W., Huang, C.C.: Multimodal sentiment analysis using hierarchical fusion with context modeling. In: Proc. 2019 International Conference on Multimodal Interaction, pp. 239\u2013243 (2019)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Xie, H., Peng, C.J., Tseng, Y.W., Chen, H.J., Hsu, C.F., Shuai, H.H., Cheng, W.H.: Emovit: Revolutionizing emotion insights with visual instruction tuning. In: IEEE Conf. Comput. Vis. Pattern Recog. pp. 26596\u201326605 (2024)","DOI":"10.1109\/CVPR52733.2024.02511"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Yang, J., Huang, Q., Ding, T., Lischinski, D., Cohen-Or, D., Huang, H.: Emoset: a large-scale visual emotion dataset with rich attributes. In: International Conference on Computer Vision, pp. 20383\u201320394 (2023)","DOI":"10.1109\/ICCV51070.2023.01864"},{"key":"3_CR24","unstructured":"Yang, S., Wang, Y., Li, Y., Wang, L., Shan, S.: A4Net: attribute-aware affective network for visual emotion recognition. IEEE Trans. Circuit Syst, Video Technol. (2024)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"You, Q., Luo, J., Jin, H., Yang, J.: Building a large-scale dataset for image emotion recognition: the fine-grained and the abstract. In: AAAI, vol.\u00a030 (2016)","DOI":"10.1609\/aaai.v30i1.9987"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing - ICIAP 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-11317-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:57:26Z","timestamp":1767322646000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-11317-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032113160","9783032113177"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-11317-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap.org\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}