{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T18:06:08Z","timestamp":1774721168734,"version":"3.50.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100016386","name":"Generalitat Valenciana (Spain), Department of Conselleria de Innovaci\u00f3n, Universidades, Ciencia y Sociedad Digital","doi-asserted-by":"publisher","award":["CIPROM\/2021\/17"],"award-info":[{"award-number":["CIPROM\/2021\/17"]}],"id":[{"id":"10.13039\/501100016386","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3584025","type":"journal-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T13:46:40Z","timestamp":1751032000000},"page":"114681-114695","source":"Crossref","is-referenced-by-count":6,"title":["Enhancing Engineering and STEM Education With Vision and Multimodal Large Language Models to Predict Student Attention"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2128-5557","authenticated-orcid":false,"given":"Luis","family":"Marquez-Carpintero","sequence":"first","affiliation":[{"name":"Institute for Computer Research, University of Alicante, Alicante, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego","family":"Viejo","sequence":"additional","affiliation":[{"name":"Institute for Computer Research, University of Alicante, Alicante, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6805-3633","authenticated-orcid":false,"given":"Miguel","family":"Cazorla","sequence":"additional","affiliation":[{"name":"Institute for Computer Research, University of Alicante, Alicante, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"in Proc. Adv. Neural Inf. Process. Syst","author":"Alayrac"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2021.102433"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/bios12070509"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1037\/1082-989X.1.2.150"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-017-2549-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app142411738"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2019.103797"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CONMEDIA53104.2021.9617173"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15354\/sief.23.re202"},{"key":"ref10","article-title":"Towards incremental learning in large language models: A critical review","volume-title":"arXiv:2404.18311","author":"Jovanovic","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78114-9_19"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2022.1118116"},{"key":"ref13","article-title":"Visualization literacy of multimodal large language models: A comparative study","volume-title":"arXiv:2407.10996","author":"Li","year":"2024"},{"key":"ref14","article-title":"Improved baselines with visual instruction tuning","volume-title":"arXiv:2310.03744","author":"Liu","year":"2023"},{"key":"ref15","article-title":"DIPSER: A dataset for in-person student engagement recognition in the wild","volume-title":"arXiv:2502.20209","author":"Marquez-Carpintero","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3415218"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/2053951720904386"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10551-019-04143-6"},{"key":"ref19","article-title":"Community-engaged programming: Applying lessons learned from the VLM green teens program","volume-title":"Proc. 21st Annu. Undergraduate Graduate Student Res. Conf. (Paideia)","author":"Organt"},{"key":"ref20","first-page":"531","article-title":"Components of visual orienting","volume":"32","author":"Posner","year":"1984","journal-title":"Attention Perform., Control Lang. Processes"},{"key":"ref21","article-title":"Learning transferable visual models from natural language supervision","volume-title":"arXiv:2103.00020","author":"Radford","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.12092"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/socsci13070381"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2023.0140371"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-64315-6_3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2019.103797"},{"key":"ref27","article-title":"llmNER: (Zero|Few)-shot named entity recognition, exploiting the power of large language models","volume-title":"arXiv:2406.04528","author":"Villena","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2024.1387089"},{"key":"ref29","article-title":"Visual prompting in multimodal large language models: A survey","volume-title":"arXiv:2409.15310","author":"Wu","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.12.003"},{"key":"ref31","article-title":"Convolution neural network hyperparameter optimization using simplified swarm optimization","volume-title":"arXiv:2103.03995","author":"Yeh","year":"2021"},{"key":"ref32","article-title":"Cognitive functions of the brain: Perception, attention and memory","volume-title":"arXiv:1907.02863","author":"Zhang","year":"2019"},{"key":"ref33","article-title":"Effectively enhancing vision language large models by prompt augmentation and caption utilization","volume-title":"arXiv:2409.14484","author":"Zhao","year":"2024"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11053810.pdf?arnumber=11053810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T17:45:40Z","timestamp":1752255940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11053810\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3584025","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}