{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:27:46Z","timestamp":1790702866206,"version":"4.1.0"},"reference-count":68,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T00:00:00Z","timestamp":1741305600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Universidad Polit\u00e9cnica de Madrid","award":["PRE2022-105516"],"award-info":[{"award-number":["PRE2022-105516"]}]},{"name":"Universidad Polit\u00e9cnica de Madrid","award":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"],"award-info":[{"award-number":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"]}]},{"name":"Universidad Polit\u00e9cnica de Madrid","award":["PID2020-118112RB-C22"],"award-info":[{"award-number":["PID2020-118112RB-C22"]}]},{"name":"Universidad Polit\u00e9cnica de Madrid","award":["PID2023-150584OB-C21"],"award-info":[{"award-number":["PID2023-150584OB-C21"]}]},{"name":"Universidad Polit\u00e9cnica de Madrid","award":["PID2021-126061OB-C43"],"award-info":[{"award-number":["PID2021-126061OB-C43"]}]},{"name":"Spanish Ministry of Education","award":["PRE2022-105516"],"award-info":[{"award-number":["PRE2022-105516"]}]},{"name":"Spanish Ministry of Education","award":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"],"award-info":[{"award-number":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"]}]},{"name":"Spanish Ministry of Education","award":["PID2020-118112RB-C22"],"award-info":[{"award-number":["PID2020-118112RB-C22"]}]},{"name":"Spanish Ministry of Education","award":["PID2023-150584OB-C21"],"award-info":[{"award-number":["PID2023-150584OB-C21"]}]},{"name":"Spanish Ministry of Education","award":["PID2021-126061OB-C43"],"award-info":[{"award-number":["PID2021-126061OB-C43"]}]},{"name":"ASTOUND","award":["PRE2022-105516"],"award-info":[{"award-number":["PRE2022-105516"]}]},{"name":"ASTOUND","award":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"],"award-info":[{"award-number":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"]}]},{"name":"ASTOUND","award":["PID2020-118112RB-C22"],"award-info":[{"award-number":["PID2020-118112RB-C22"]}]},{"name":"ASTOUND","award":["PID2023-150584OB-C21"],"award-info":[{"award-number":["PID2023-150584OB-C21"]}]},{"name":"ASTOUND","award":["PID2021-126061OB-C43"],"award-info":[{"award-number":["PID2021-126061OB-C43"]}]},{"DOI":"10.13039\/501100004837","name":"GOMINOLA","doi-asserted-by":"publisher","award":["PRE2022-105516"],"award-info":[{"award-number":["PRE2022-105516"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"GOMINOLA","doi-asserted-by":"publisher","award":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"],"award-info":[{"award-number":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"GOMINOLA","doi-asserted-by":"publisher","award":["PID2020-118112RB-C22"],"award-info":[{"award-number":["PID2020-118112RB-C22"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"GOMINOLA","doi-asserted-by":"publisher","award":["PID2023-150584OB-C21"],"award-info":[{"award-number":["PID2023-150584OB-C21"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"GOMINOLA","doi-asserted-by":"publisher","award":["PID2021-126061OB-C43"],"award-info":[{"award-number":["PID2021-126061OB-C43"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"TRUSTBOOST","doi-asserted-by":"publisher","award":["PRE2022-105516"],"award-info":[{"award-number":["PRE2022-105516"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"TRUSTBOOST","doi-asserted-by":"publisher","award":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"],"award-info":[{"award-number":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"TRUSTBOOST","doi-asserted-by":"publisher","award":["PID2020-118112RB-C22"],"award-info":[{"award-number":["PID2020-118112RB-C22"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"TRUSTBOOST","doi-asserted-by":"publisher","award":["PID2023-150584OB-C21"],"award-info":[{"award-number":["PID2023-150584OB-C21"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"TRUSTBOOST","doi-asserted-by":"publisher","award":["PID2021-126061OB-C43"],"award-info":[{"award-number":["PID2021-126061OB-C43"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"BeWord","doi-asserted-by":"publisher","award":["PRE2022-105516"],"award-info":[{"award-number":["PRE2022-105516"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"BeWord","doi-asserted-by":"publisher","award":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"],"award-info":[{"award-number":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"BeWord","doi-asserted-by":"publisher","award":["PID2020-118112RB-C22"],"award-info":[{"award-number":["PID2020-118112RB-C22"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"BeWord","doi-asserted-by":"publisher","award":["PID2023-150584OB-C21"],"award-info":[{"award-number":["PID2023-150584OB-C21"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"BeWord","doi-asserted-by":"publisher","award":["PID2021-126061OB-C43"],"award-info":[{"award-number":["PID2021-126061OB-C43"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MCIN\/AEI\/10.13039\/501100011033","award":["PRE2022-105516"],"award-info":[{"award-number":["PRE2022-105516"]}]},{"name":"MCIN\/AEI\/10.13039\/501100011033","award":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"],"award-info":[{"award-number":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"]}]},{"name":"MCIN\/AEI\/10.13039\/501100011033","award":["PID2020-118112RB-C22"],"award-info":[{"award-number":["PID2020-118112RB-C22"]}]},{"name":"MCIN\/AEI\/10.13039\/501100011033","award":["PID2023-150584OB-C21"],"award-info":[{"award-number":["PID2023-150584OB-C21"]}]},{"name":"MCIN\/AEI\/10.13039\/501100011033","award":["PID2021-126061OB-C43"],"award-info":[{"award-number":["PID2021-126061OB-C43"]}]},{"name":"European Union \u201cNextGenerationEU\/PRTR\u201d","award":["PRE2022-105516"],"award-info":[{"award-number":["PRE2022-105516"]}]},{"name":"European Union \u201cNextGenerationEU\/PRTR\u201d","award":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"],"award-info":[{"award-number":["101071191\u2014HORIZON-EIC-2021-PATHFINDERCHALLENGES-01"]}]},{"name":"European Union \u201cNextGenerationEU\/PRTR\u201d","award":["PID2020-118112RB-C22"],"award-info":[{"award-number":["PID2020-118112RB-C22"]}]},{"name":"European Union \u201cNextGenerationEU\/PRTR\u201d","award":["PID2023-150584OB-C21"],"award-info":[{"award-number":["PID2023-150584OB-C21"]}]},{"name":"European Union \u201cNextGenerationEU\/PRTR\u201d","award":["PID2021-126061OB-C43"],"award-info":[{"award-number":["PID2021-126061OB-C43"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The accurate modelling of video memorability, or the intrinsic properties that render a piece of audiovisual content more likely to be remembered, will facilitate the development of automatic systems that are more efficient in retrieving, classifying and generating impactful media. Recent studies have indicated a strong correlation between the visual semantics of video and its memorability. This underscores the importance of developing advanced visual comprehension abilities to enhance model performance. It has been demonstrated that Large Vision\u2013Language Models (LVLMs) demonstrate exceptional proficiency in generalist, high-level semantic comprehension of images and video, due to their extensive multimodal pre-training on a vast scale. This work makes use of the vast generalist knowledge of LVLMs and explores efficient adaptation techniques with a view to utilising them as memorability predictors. In particular, the Quantized Low-Rank Adaptation (QLoRA) technique is employed to fine-tune the Qwen-VL model with memorability-related data extracted from the Memento10k dataset. In light of existing research, we propose a particular methodology that transforms Qwen-VL from a language model to a memorability score regressor. Furthermore, we consider the influence of selecting appropriate LoRA hyperparameters, a design aspect that has been insufficiently studied. We validate the LoRA rank and alpha hyperparameters using 5-Fold Cross-Validation and evaluate our best configuration on the official testing portion of the Memento10k dataset, obtaining a state-of-the-art Spearman Rank Correlation Coefficient (SRCC) of 0.744. Consequently, this work represents a significant advancement in modelling video memorability through high-level semantic understanding.<\/jats:p>","DOI":"10.3390\/s25061661","type":"journal-article","created":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T12:22:52Z","timestamp":1741350172000},"page":"1661","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Parameter-Efficient Adaptation of Large Vision\u2014Language Models for Video Memorability Prediction"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2769-9752","authenticated-orcid":false,"given":"Iv\u00e1n","family":"Mart\u00edn-Fern\u00e1ndez","sequence":"first","affiliation":[{"name":"Grupo de Tecnolog\u00eda del Habla y Aprendizaje Autom\u00e1tico (THAU Group), Information Processing and Telecommunications Center, E.T.S.I. de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid (UPM), 28040 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6336-7877","authenticated-orcid":false,"given":"Sergio","family":"Esteban-Romero","sequence":"additional","affiliation":[{"name":"Grupo de Tecnolog\u00eda del Habla y Aprendizaje Autom\u00e1tico (THAU Group), Information Processing and Telecommunications Center, E.T.S.I. de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid (UPM), 28040 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3877-0089","authenticated-orcid":false,"given":"Fernando","family":"Fern\u00e1ndez-Mart\u00ednez","sequence":"additional","affiliation":[{"name":"Grupo de Tecnolog\u00eda del Habla y Aprendizaje Autom\u00e1tico (THAU Group), Information Processing and Telecommunications Center, E.T.S.I. de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid (UPM), 28040 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-6224","authenticated-orcid":false,"given":"Manuel","family":"Gil-Mart\u00edn","sequence":"additional","affiliation":[{"name":"Grupo de Tecnolog\u00eda del Habla y Aprendizaje Autom\u00e1tico (THAU Group), Information Processing and Telecommunications Center, E.T.S.I. de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid (UPM), 28040 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,7]]},"reference":[{"key":"ref_1","unstructured":"Memorable.io (2025, March 04). Memorable.io: AI-Powered Memorability Prediction. Available online: https:\/\/www.memorable.io\/."},{"key":"ref_2","unstructured":"Neosperience (2025, March 04). Image Memorability by Neosperience. Available online: https:\/\/image.neosperience.com\/."},{"key":"ref_3","unstructured":"Needell, C.D. (2025, March 04). Resmem: A Package that Wraps the ResMem Pytorch Model. Available online: https:\/\/github.com\/Brain-Bridge-Lab\/resmem."},{"key":"ref_4","unstructured":"Bernstein, D.A., and Nash, P.W. (2008). Sensation and Perception. Essentials of Psychology, Houghton Mifflin Company."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1348\/0007126042369811","article-title":"A model of aesthetic appreciation and aesthetic judgments","volume":"95","author":"Leder","year":"2004","journal-title":"Br. J. Psychol."},{"key":"ref_6","unstructured":"Bernstein, D.A., and Nash, P.W. (2008). Memory. Essentials of Psychology, Houghton Mifflin Company."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Isola, P., Xiao, J., Torralba, A., and Oliva, A. (2011, January 20\u201325). What makes an image memorable?. Proceedings of the CVPR 2011 IEEE, Colorado Springs, CO, USA.","DOI":"10.1109\/CVPR.2011.5995721"},{"key":"ref_8","first-page":"2429","article-title":"Understanding the intrinsic memorability of images","volume":"24","author":"Isola","year":"2011","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"104714","DOI":"10.1016\/j.cognition.2021.104714","article-title":"Visual memorability in the absence of semantic content","volume":"212","author":"Lin","year":"2021","journal-title":"Cognition"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1038\/s41562-020-0901-2","article-title":"Memorability of words in arbitrary verbal associations modulates memory retrieval in the anterior temporal lobe","volume":"4","author":"Xie","year":"2020","journal-title":"Nat. Hum. Behav."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Bylinskii, Z., Goetschalckx, L., Newman, A., and Oliva, A. (2022). Memorability: An image-computable measure of information utility. Human Perception of Visual Information: Psychological and Computational Perspectives, Springer.","DOI":"10.1007\/978-3-030-81465-6_8"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kleinlein, R., Luna-Jim\u00e9nez, C., Arias-Cuadrado, D., Ferreiros, J., and Fern\u00e1ndez-Mart\u00ednez, F. (2021). Topic-Oriented Text Features Can Match Visual Deep Models of Video Memorability. Appl. Sci., 11.","DOI":"10.3390\/app11167406"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., and Parikh, D. (2017, January 21\u201326). Making the v in vqa matter: Elevating the role of image understanding in visual question answering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref_14","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","unstructured":"Agrawal, H., Desai, K., Wang, Y., Chen, X., Jain, R., Johnson, M., Batra, D., Parikh, D., Lee, S., and Anderson, P. (November, January 27). Nocaps: Novel object captioning at scale. Proceedings of the IEEE\/CVF international Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","article-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","volume":"2","author":"Young","year":"2014","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., and Berg, T. (2014, January 25\u201329). Referitgame: Referring to objects in photographs of natural scenes. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Newman, A., Fosco, C., Casser, V., Lee, A., McNamara, B., and Oliva, A. (2020, January 23\u201328). Multimodal memorability: Modeling effects of semantics and decay on video memorability. Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XVI 16.","DOI":"10.1007\/978-3-030-58517-4_14"},{"key":"ref_19","unstructured":"Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., and Zhou, J. (2023). Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv."},{"key":"ref_20","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2021). LoRA: Low-Rank Adaptation of Large Language Models. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/S0022-5371(67)80067-7","article-title":"Recognition memory for words, sentences, and pictures","volume":"6","author":"Shepard","year":"1967","journal-title":"J. Verbal Learn. Verbal Behav."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1080\/14640747308400340","article-title":"Learning 10,000 pictures","volume":"25","author":"Standing","year":"1973","journal-title":"Q. J. Exp. Psychol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e47596","DOI":"10.7554\/eLife.47596","article-title":"Population response magnitude variation in inferotemporal cortex predicts image memorability","volume":"8","author":"Jaegle","year":"2019","journal-title":"eLife"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lahner, B., Mohsenzadeh, Y., Mullin, C., and Oliva, A. (2024). Visual perception of highly memorable images is mediated by a distributed network of ventral visual regions that enable a late memorability response. PLoS Biol., 22.","DOI":"10.1371\/journal.pbio.3002564"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Perera, S., Tal, A., and Zelnik-Manor, L. (2019, January 15\u201320). Is image memorability prediction solved?. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00108"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Khosla, A., Raju, A.S., Torralba, A., and Oliva, A. (2015, January 7\u201313). Understanding and predicting image memorability at a large scale. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.275"},{"key":"ref_27","unstructured":"Cohendet, R., Demarty, C.H., Duong, N.Q., and Engilberge, M. (November, January 27). VideoMem: Constructing, analyzing, predicting short-term and long-term video memorability. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_28","unstructured":"Constantin, M.G., Demarty, C.H., Fosco, C., Seco, A.G., de Herrera, S.H., Healy, G., Ionescu, B., Matran-Fernandez, A., Kiziltepe, R.S., and Smeaton, A.F. (2024, January 1\u20132). Overview of The MediaEval 2023 Predicting Video Memorability Task. Proceedings of the MediaEval \u201923: Multimedia Evaluation Workshop, Amsterdam, The Netherlands."},{"key":"ref_29","unstructured":"Sweeney, L., Constantin, M.G., Demarty, C.H., Fosco, C., de Herrera, A.G.S., Halder, S., Healy, G., Ionescu, B., Matran-Fernandez, A., and Smeaton, A.F. (2022). Overview of the MediaEval 2022 predicting video memorability task. arXiv."},{"key":"ref_30","unstructured":"Kiziltepe, R.S., Constantin, M.G., Demarty, C.H., Healy, G., Fosco, C., de Herrera, A.G.S., Halder, S., Ionescu, B., Matran-Fernandez, A., and Smeaton, A.F. (2021). Overview of the MediaEval 2021 predicting media memorability task. arXiv."},{"key":"ref_31","unstructured":"Constantin, M.G., and Ionescu, B. (2023, January 13\u201315). AIMultimediaLab at MediaEval 2022: Predicting Media Memorability Using Video Vision Transformers and Augmented Memorable Moments. Proceedings of the MediaEval \u201923: Multimedia Evaluation Workshop, Bergen, Norway."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Mart\u00edn-Fern\u00e1ndez, I., Kleinlein, R., Luna-Jim\u00e9nez, C., Gil-Mart\u00edn, M., and Fern\u00e1ndez-Mart\u00ednez, F. (2023, January 20\u201322). Video Memorability Prediction From Jointly-learnt Semantic and Visual Features. Proceedings of the 20th International Conference on Content-Based Multimedia Indexing, New York, NY, USA.","DOI":"10.1145\/3617233.3617260"},{"key":"ref_33","unstructured":"Agarla, M., Celona, L., and Schettini, R. (2023, January 12\u201313). Predicting Video Memorability Using a Model Pretrained with Natural Language Supervision. Proceedings of the MediaEval Multimedia Benchmark Workshop Working Notes, Bergen, Norway and Online."},{"key":"ref_34","unstructured":"Kleinlein, R., Luna-Jim\u00e9nez, C., and Fern\u00e1ndez-Mart\u00ednez, F. (2021, January 13\u201315). THAU-UPM at MediaEval 2021: From Video Semantics To Memorability Using Pretrained Transformers. Proceedings of the MediaEval Multimedia Benchmark Workshop Working Notes, Online."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Dumont, T., Hevia, J.S., and Fosco, C.L. (2023, January 17\u201324). Modular memorability: Tiered representations for video memorability prediction. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01035"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, J., Guo, X., Yue, F., Xue, F., and Sun, J. (2022). Adaptive Multi-Modal Ensemble Network for Video Memorability Prediction. Appl. Sci., 12.","DOI":"10.3390\/app12178599"},{"key":"ref_37","unstructured":"Kumar, P., Khandelwal, E., Tapaswi, M., and Sreekumar, V. (2024). Seeing Eye to AI: Comparing Human Gaze and Model Attention in Video Memorability. arXiv."},{"key":"ref_38","first-page":"1","article-title":"Can GPT-3 pass a Writer\u2019s turing test?","volume":"5","author":"Elkins","year":"2020","journal-title":"J. Cult. Anal."},{"key":"ref_39","unstructured":"Kosinski, M. (2023). Theory of mind may have spontaneously emerged in large language models. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Yukun, Z., Xu, L., Huang, Z., Peng, K., Seligman, M., Li, E., and Yu, F. (2023). AI Chatbot Responds to Emotional Cuing. PsyArXiv, preprint.","DOI":"10.31234\/osf.io\/9ymfz"},{"key":"ref_41","unstructured":"Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y.T., Li, Y., and Lundberg, S. (2023). Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv."},{"key":"ref_42","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017, January 4\u20139). Attention is All you Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_43","unstructured":"Team, G., Anil, R., Borgeaud, S., Alayrac, J.B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A.M., Hauth, A., and Millican, K. (2023). Gemini: A family of highly capable multimodal models. arXiv."},{"key":"ref_44","unstructured":"Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Yang, A., and Fan, A. (2024). The llama 3 herd of models. arXiv."},{"key":"ref_45","unstructured":"OpenAI (2023). GPT-4 Technical Report. arXiv."},{"key":"ref_46","unstructured":"Yang, A., Yang, B., Hui, B., Zheng, B., Yu, B., Zhou, C., Li, C., Li, C., Liu, D., and Huang, F. (2024). Qwen2 Technical Report. arXiv."},{"key":"ref_47","unstructured":"Anthropic (2024). Claude 3.5 Sonnet Model Card Addendum, Anthropic."},{"key":"ref_48","unstructured":"Team, G., Riviere, M., Pathak, S., Sessa, P.G., Hardin, C., Bhupatiraju, S., Hussenot, L., Mesnard, T., Shahriari, B., and Ram\u00e9, A. (2024). Gemma 2: Improving open language models at a practical size. arXiv."},{"key":"ref_49","unstructured":"Qwen Team (2025). Qwen2.5 Technical Report. arXiv."},{"key":"ref_50","unstructured":"Meta (2024, November 25). Llama 3.2 Model Card. Available online: https:\/\/github.com\/meta-llama\/llama-models\/blob\/main\/models\/llama3_2\/MODEL_CARD.md."},{"key":"ref_51","unstructured":"Beyer, L., Steiner, A., Pinto, A.S., Kolesnikov, A., Wang, X., Salz, D., Neumann, M., Alabdulmohsin, I., Tschannen, M., and Bugliarello, E. (2024). Paligemma: A versatile 3b vlm for transfer. arXiv."},{"key":"ref_52","unstructured":"Liu, H., Li, C., Wu, Q., and Lee, Y.J. (2024, January 10\u201316). Visual Instruction Tuning. Proceedings of the NeurIPS, New Orleans, LA, USA."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., and Lee, Y.J. (2024, January 17\u201321). Improved Baselines with Visual Instruction Tuning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle WA, USA.","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"de Zarz\u00e0, I., de Curt\u00f2, J., Roig, G., and Calafate, C.T. (2023). LLM Multimodal Traffic Accident Forecasting. Sensors, 23.","DOI":"10.3390\/s23229225"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Acharya, A., Saha, S., Jain, V., and Chadha, A. (2024). Exploring the frontier of vision-language models: A survey of current methodologies and future directions. arXiv.","DOI":"10.2139\/ssrn.4783140"},{"key":"ref_56","unstructured":"Singh, S., Si, H., Singla, Y.K., Baths, V., Shah, R.R., Chen, C., and Krishnamurthy, B. (2024). LLaVA Finds Free Lunch: Teaching Human Behavior Improves Content Understanding Abilities Of LLMs. arXiv."},{"key":"ref_57","unstructured":"au2, H.S.I., Singh, S., Singla, Y.K., Bhattacharyya, A., Baths, V., Chen, C., Shah, R.R., and Krishnamurthy, B. (2024). Long-Term Ad Memorability: Understanding and Generating Memorable Ads. arXiv."},{"key":"ref_58","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., and Cao, Y. (2023). Eva-clip: Improved training techniques for clip at scale. arXiv."},{"key":"ref_59","unstructured":"Nguyen, M.Q., Trinh, M.H., Bui, H.G., Vo, K.T., Tran, M.T., Tran, T.P., and Nguyen, H.D. (2023, January 12\u201313). SELAB-HCMUS at MediaEval 2023: A cross-domain and subject-centric approach towards the memorability prediction task. Proceedings of the MediaEval Multimedia Benchmark Workshop Working Notes, Bergen, Norway and Online."},{"key":"ref_60","unstructured":"Usmani, M.M.A., Zahid, S., and Tahir, M.A. (2023, January 13\u201315). Modelling of Video Memorability using Ensemble Learning and Transformers. Proceedings of the MediaEval\u201922: Multimedia Evaluation Workshop, Bergen, Norway."},{"key":"ref_61","unstructured":"Azzakhnini, S., Ahmed, O.B., and Fernandez-Maloigne, C. (2023, January 13\u201315). Video Memorability Prediction using Deep Features and Loss-based Memorability Distribution Estimation. Proceedings of the MediaEval\u201922: Multimedia Evaluation Workshop, Bergen, Norway."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Sweeney, L., Smeaton, A., and Healy, G. (2023, January 20\u201322). Memories in the Making: Predicting Video Memorability with Encoding Phase EEG. Proceedings of the 20th International Conference on Content-Based Multimedia Indexing, Orleans, France.","DOI":"10.1145\/3617233.3617266"},{"key":"ref_63","unstructured":"Esteban-Romero, S., Bellver-Soler, J., Mart\u0131n-Fern\u00e1ndez, I., Gil-Mart\u0131n, M., D\u2019Haro, L.F., and Fern\u00e1ndez-Mart\u0131nez, F. (2024, January 24). THAU-UPM at EmoSPeech-IberLEF2024: Efficient Adaptation of Mono-modal and Multi-modal Large Language Models for Automatic Speech Emotion Recognition. 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), Castilla y Le\u00f3n, Spain."},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Esteban-Romero, S., Mart\u00edn-Fern\u00e1ndez, I., Gil-Mart\u00edn, M., and Fern\u00e1ndez-Mart\u00ednez, F. (2025, March 04). Synthesizing Olfactory Understanding: Multimodal Language Models for Image-Text Smell Matching. Available online: https:\/\/ssrn.com\/abstract=4912100.","DOI":"10.2139\/ssrn.4912100"},{"key":"ref_65","first-page":"10088","article-title":"QLoRA: Efficient Finetuning of Quantized LLMs","volume":"Volume 36","author":"Oh","year":"2023","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Li, K., Yang, Z., Chen, L., Yang, Y., and Xiao, J. (2023, January 20\u201322). CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation. Proceedings of the 31st ACM International Conference on Multimedia, New York, NY, USA.","DOI":"10.1145\/3581783.3611724"},{"key":"ref_67","unstructured":"Salakhutdinov, R., Kolter, Z., Heller, K., Weller, A., Oliver, N., Scarlett, J., and Berkenkamp, F. (2024, January 21\u201327). DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent). Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_68","unstructured":"Xiong, H., Yang, Z., Yu, J., Zhuge, Y., Zhang, L., Zhu, J., and Lu, H. (2025, January 24\u201328). Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge. Proceedings of the Thirteenth International Conference on Learning Representations, Singapore."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/6\/1661\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:49:08Z","timestamp":1760028548000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/6\/1661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,7]]},"references-count":68,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["s25061661"],"URL":"https:\/\/doi.org\/10.3390\/s25061661","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,7]]}}}