{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T12:29:40Z","timestamp":1771244980559,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569496","type":"print"},{"value":"9789819569502","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\/978-981-95-6950-2_8","type":"book-chapter","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:58:44Z","timestamp":1771243124000},"page":"103-116","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Case Study on\u00a0Large Visual-Language Model Attention Explainability After Adaptation Using Persuasion Strategies in\u00a0Advertisements"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2769-9752","authenticated-orcid":false,"given":"Iv\u00e1n","family":"Mart\u00edn-Fern\u00e1ndez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2312-6672","authenticated-orcid":false,"given":"Mihai Gabriel","family":"Constantin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0535-1306","authenticated-orcid":false,"given":"Bogdan","family":"Ionescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6336-7877","authenticated-orcid":false,"given":"Sergio","family":"Esteban-Romero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3877-0089","authenticated-orcid":false,"given":"Fernando","family":"Fern\u00e1ndez-Mart\u00ednez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-6224","authenticated-orcid":false,"given":"Manuel","family":"Gil-Mart\u00edn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","unstructured":"Bellver, J., et al.: Multimodal audio-language model for speech emotion recognition. In: The Speaker and Language Recognition Workshop, Odyssey 2024, pp. 288\u2013295 (2024). https:\/\/doi.org\/10.21437\/odyssey.2024-41","DOI":"10.21437\/odyssey.2024-41"},{"key":"8_CR2","unstructured":"Beyer, L., et\u00a0al.: PaliGemma: a versatile 3B VLM for transfer. arXiv preprint arXiv:2407.07726 (2024)"},{"key":"8_CR3","doi-asserted-by":"publisher","unstructured":"Bhattacharyya, A., Singla, Y.K., Krishnamurthy, B., Shah, R.R., Chen, C.: A video is worth 4096 tokens: Verbalize videos to understand them in zero shot. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, December 2023, pp. 9822\u20139839. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.608, https:\/\/aclanthology.org\/2023.emnlp-main.608","DOI":"10.18653\/v1\/2023.emnlp-main.608"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Bi, J., et al.: Unveiling visual perception in language models: an attention head analysis approach. In: Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), pp. 4135\u20134144 (June 2025)","DOI":"10.1109\/CVPR52734.2025.00391"},{"issue":"2","key":"8_CR5","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1108\/JSIT-07-2022-0166","volume":"25","author":"A Braca","year":"2023","unstructured":"Braca, A., Dondio, P.: Persuasive communication systems: a machine learning approach to predict the effect of linguistic styles and persuasion techniques. J. Syst. Inf. Technol. 25(2), 160\u2013191 (2023). https:\/\/doi.org\/10.1108\/JSIT-07-2022-0166","journal-title":"J. Syst. Inf. Technol."},{"key":"8_CR6","unstructured":"Cialdini, R.B.: The science of Persuasion. Sci. Am. Mind 14(1), 70\u201377 (2004). http:\/\/www.jstor.org\/stable\/24939368"},{"key":"8_CR7","doi-asserted-by":"publisher","unstructured":"Da\u00a0San\u00a0Martino, G., Barr\u00f3n-Cede\u00f1o, A., Nakov, P., Glass, M.: Fine-grained analysis of propaganda in news articles. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp. 5636\u20135646 (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1565","DOI":"10.18653\/v1\/D19-1565"},{"key":"8_CR8","unstructured":"Esteban-Romero, S., et al.: THAU-UPM at EmoSpeech-IberLEF2024: efficient adaptation of mono-modal and multi-modal large language models for automatic speech emotion recognition. In: Proceedings of the Iberian Languages Evaluation Forum, IberLEF 2024, co-located with the 40th Conference of the Spanish Society for Natural Language Processing, SEPLN 2024. CEUR-WS. org. Conference of the Spanish Society for Natural Language Processing (SEPLN 2024), CEUR-WS. org (2024)"},{"key":"8_CR9","doi-asserted-by":"publisher","unstructured":"Esteban-Romero, S., et al.: LLM-driven multimodal fusion for human perception analysis. In: Proceedings of the 5th on Multimodal Sentiment Analysis Challenge and Workshop: Social Perception and Humor, MuSe\u201924, pp. 45\u201351. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3689062.3689084","DOI":"10.1145\/3689062.3689084"},{"key":"8_CR10","unstructured":"Han, J., et al.: ImageBind-LLM: multi-modality instruction tuning (2023). https:\/\/arxiv.org\/abs\/2309.03905"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Hussain, Z., et al.: Automatic understanding of image and video advertisements. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1705\u20131715 (2017)","DOI":"10.1109\/CVPR.2017.123"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Kaduri, O., Bagon, S., Dekel, T.: What\u2019s in the image? A deep-dive into the vision of vision language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), June 2025, pp. 14549\u201314558 (2025)","DOI":"10.1109\/CVPR52734.2025.01356"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Kumar, Y., et al.: Persuasion strategies in advertisements. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 57\u201366 (2023)","DOI":"10.1609\/aaai.v37i1.25076"},{"issue":"4","key":"8_CR14","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1086\/605297","volume":"36","author":"L Lau-Gesk","year":"2009","unstructured":"Lau-Gesk, L., Meyers-Levy, J.: Emotional persuasion: when the valence versus the resource demands of emotions influence consumers\u2019 attitudes. J. Consum. Res. 36(4), 585\u2013599 (2009). https:\/\/doi.org\/10.1086\/605297","journal-title":"J. Consum. Res."},{"key":"8_CR15","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: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th International Conference on Machine Learning, 23\u201329 July 2023, vol.\u00a0202, pp. 19730\u201319742. Proceedings of Machine Learning Research. PMLR (2023). https:\/\/proceedings.mlr.press\/v202\/li23q.html"},{"key":"8_CR16","doi-asserted-by":"publisher","unstructured":"Mart\u00edn-Fern\u00e1ndez, I., Esteban-Romero, S., Bellver-Soler, J., Fern\u00e1ndez-Mart\u00ednez, F., Gil-Mart\u00edn, M.: Larger encoders, smaller regressors: exploring label dimensionality reduction and multimodal large language models as feature extractors for predicting social perception. In: Proceedings of the 5th on Multimodal Sentiment Analysis Challenge and Workshop: Social Perception and Humor, MuSe\u201924, pp. 20\u201327. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3689062.3689083","DOI":"10.1145\/3689062.3689083"},{"key":"8_CR17","unstructured":"Neo, C., Ong, L., Torr, P., Geva, M., Krueger, D., Barez, F.: Towards interpreting visual information processing in vision-language models. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=chanJGoa7f"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Pryzant, R., Shen, K., Jurafsky, D., Wagner, S.: Deconfounded lexicon induction for interpretable social science. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1615\u20131625 (2018)","DOI":"10.18653\/v1\/N18-1146"},{"key":"8_CR19","unstructured":"Steiner, A., et\u00a0al.: PaliGemma 2: a family of versatile VLMs for transfer. arXiv preprint arXiv:2412.03555 (2024)"},{"key":"8_CR20","unstructured":"Team, G., et\u00a0al.: Gemma: open models based on Gemini research and technology. arXiv preprint arXiv:2403.08295 (2024)"},{"key":"8_CR21","unstructured":"Vorakitphan, V., Cabrio, E., Villata, S.: \u201cdon\u2019t discuss\u201d: investigating semantic and argumentative features for supervised propagandist message detection and classification. In: Recent Advances in Natural Language Processing, RANLP 2021 (2021)"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01100"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6950-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:58:48Z","timestamp":1771243128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6950-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569496","9789819569502"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6950-2_8","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":"17 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}