{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T10:08:21Z","timestamp":1774606101308,"version":"3.50.1"},"reference-count":88,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T00:00:00Z","timestamp":1771804800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":32,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-39584-3","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T19:46:12Z","timestamp":1771875972000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FaceScanPaliGemma multi-agent vision language models for facial attribute recognition"],"prefix":"10.1038","volume":"16","author":[{"given":"Nouar","family":"AlDahoul","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Myles Joshua Toledo","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harishwar Reddy","family":"Kasireddy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasir","family":"Zaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"key":"39584_CR1","doi-asserted-by":"publisher","unstructured":"Karkkainen, K. & Joo, J. Fairface: Face attribute dataset for balanced race, gender, and age for bias measurement and mitigation. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision, 1548\u20131558 (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00159.","DOI":"10.1109\/WACV48630.2021.00159"},{"key":"39584_CR2","unstructured":"Yuan, H., He, Y., Du, P. & Song, L. Multi-task learning using uncertainty to weigh losses for heterogeneous face attribute estimation. arXiv preprint arXiv:2403.00561 (2024)."},{"key":"39584_CR3","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1109\/TAFFC.2014.2346515","volume":"5","author":"SH Lee","year":"2014","unstructured":"Lee, S. H., Plataniotis, K. N. & Ro, Y. M. Intra-class variation reduction using training expression images for sparse representation based facial expression recognition. IEEE Trans Affective Comput 5, 340\u2013351. https:\/\/doi.org\/10.1109\/TAFFC.2014.2346515 (2014).","journal-title":"IEEE Trans Affective Comput"},{"key":"39584_CR4","unstructured":"Singh Sengar, S., Hasan, A.\u00a0B., Kumar, S. & Carroll, F. Generative artificial intelligence: A systematic review and applications. arXiv e-prints arXiv\u20132405 (2024). arXiv:2405.11029."},{"key":"39584_CR5","unstructured":"Belcak, P. et al. Small language models are the future of agentic ai. arXiv preprint arXiv:2506.02153 (2025)."},{"key":"39584_CR6","unstructured":"Murugappan, G. Multiagent Debate among Vision-Language Models Improves Multimodal Reasoning. Master\u00e2\u20ac\u2122s thesis, Georgia Institute of Technology, Atlanta, GA (2024)."},{"key":"39584_CR7","unstructured":"Ali, M.\u00a0H. & Rasheed, M.\u00a0A. A blockchain-based multi-agent security framework for e-commerce systems. International Journal of Theoretical & Applied Computational Intelligence (2025). URL https:\/\/orcid.org\/0000-0001-7963-0918."},{"key":"39584_CR8","unstructured":"Hosseini, M.\u00a0M., Fard, A.\u00a0P. & Mahoor, M.\u00a0H. Faces of fairness: Examining bias in facial expression recognition datasets and models. arXiv preprint arXiv:2502.11049 (2025)."},{"key":"39584_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110173","volume":"148","author":"J Jiang","year":"2024","unstructured":"Jiang, J., Wang, M., Xiao, B., Hu, J. & Deng, W. Joint recognition of basic and compound facial expressions by mining latent soft labels. Pattern Recognition 148, 110173. https:\/\/doi.org\/10.1016\/j.patcog.2023.110173 (2024).","journal-title":"Pattern Recognition"},{"key":"39584_CR10","doi-asserted-by":"publisher","unstructured":"Hosseini, M.\u00a0M. & Jamzad, M. Facial mark detection and removal using graph relations and statistics. In 2017 Iranian Conference on Electrical Engineering (ICEE), 2223\u20132228 (IEEE, 2017). https:\/\/doi.org\/10.1109\/IranianCEE.2017.7985432.","DOI":"10.1109\/IranianCEE.2017.7985432"},{"key":"39584_CR11","doi-asserted-by":"crossref","unstructured":"Yang, D. et al. Robust emotion recognition in context debiasing. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 12447\u201312457 (2024).","DOI":"10.1109\/CVPR52733.2024.01183"},{"key":"39584_CR12","doi-asserted-by":"publisher","unstructured":"Yu, J. et al. Exploring facial expression recognition through semi-supervised pre-training and temporal modeling. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 4880\u20134887 (2024). https:\/\/doi.org\/10.1109\/CVPRW63382.2024.00492.","DOI":"10.1109\/CVPRW63382.2024.00492"},{"key":"39584_CR13","doi-asserted-by":"publisher","unstructured":"Liang, H., Perona, P. & Balakrishnan, G. Benchmarking algorithmic bias in face recognition: An experimental approach using synthetic faces and human evaluation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 4977\u20134987 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00459.","DOI":"10.1109\/ICCV51070.2023.00459"},{"key":"39584_CR14","doi-asserted-by":"publisher","first-page":"74500","DOI":"10.1109\/ACCESS.2023.3293852","volume":"11","author":"A Hafeez","year":"2023","unstructured":"Hafeez, A. et al. Addressing imbalance problem for multi label classification of scholarly articles. IEEE Access 11, 74500\u201374516. https:\/\/doi.org\/10.1109\/ACCESS.2023.3293852 (2023).","journal-title":"IEEE Access"},{"key":"39584_CR15","doi-asserted-by":"publisher","unstructured":"Schroff, F., Kalenichenko, D. & Philbin, J. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition, 815\u2013823 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298682.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"39584_CR16","doi-asserted-by":"publisher","unstructured":"Mustapha, M.\u00a0F., Mohamad, N.\u00a0M., Osman, G. & Ab Hamid, S.\u00a0H. Age group classification using convolutional neural network (cnn). In Journal of Physics: Conference Series, vol. 2084, 012028 (IOP Publishing, 2021). https:\/\/doi.org\/10.1088\/1742-6596\/2084\/1\/012028.","DOI":"10.1088\/1742-6596\/2084\/1\/012028"},{"key":"39584_CR17","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"key":"39584_CR18","doi-asserted-by":"publisher","first-page":"14449","DOI":"10.1038\/s41598-025-99623-3","volume":"15","author":"N AlDahoul","year":"2025","unstructured":"AlDahoul, N., Rahwan, T. & Zaki, Y. Ai-generated faces influence gender stereotypes and racial homogenization. Scientific reports 15, 14449. https:\/\/doi.org\/10.1038\/s41598-025-99623-3 (2025).","journal-title":"Scientific reports"},{"key":"39584_CR19","doi-asserted-by":"publisher","unstructured":"Cao, Q., Shen, L., Xie, W., Parkhi, O.\u00a0M. & Zisserman, A. Vggface2: A dataset for recognising faces across pose and age. In 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018), 67\u201374 (IEEE, 2018). https:\/\/doi.org\/10.1109\/FG.2018.00020.","DOI":"10.1109\/FG.2018.00020"},{"key":"39584_CR20","unstructured":"Tan, M. & Le, Q.\u00a0V. Efficientnet: Rethinking model scaling for convolutional neural networks. CoRR arXiv:1905.11946 (2019)."},{"key":"39584_CR21","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (2021). https:\/\/doi.org\/10.48550\/arXiv.2010.11929.","DOI":"10.48550\/arXiv.2010.11929"},{"key":"39584_CR22","doi-asserted-by":"publisher","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In International conference on machine learning, 8748\u20138763 (PMLR, 2021). https:\/\/doi.org\/10.48550\/arXiv.2103.00020.","DOI":"10.48550\/arXiv.2103.00020"},{"key":"39584_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TAFFC.2017.2740923","volume":"99","author":"A Mollahosseini","year":"2008","unstructured":"Mollahosseini, A., Hasani, B. & Mahoor, M. Affectnet: a new database for facial expression, valence, and arousal computation in the wild. IEEE Trans. Affect. Comput. 99, 1\u20131. https:\/\/doi.org\/10.1109\/TAFFC.2017.2740923 (2008).","journal-title":"IEEE Trans. Affect. Comput."},{"key":"39584_CR24","unstructured":"Ning, M., Salah, A.\u00a0A. & Ertugrul, I.\u00a0O. Representation learning and identity adversarial training for facial behavior understanding. arXiv preprint arXiv:2407.11243 (2024)."},{"key":"39584_CR25","unstructured":"Mao, J. et al. Poster++: A simpler and stronger facial expression recognition network. arXiv preprint arXiv:2301.12149 (2023)."},{"key":"39584_CR26","doi-asserted-by":"publisher","first-page":"2132","DOI":"10.1109\/TAFFC.2022.3188390","volume":"13","author":"AV Savchenko","year":"2022","unstructured":"Savchenko, A. V., Savchenko, L. V. & Makarov, I. Classifying emotions and engagement in online learning based on a single facial expression recognition neural network. IEEE Transa. Affective Comput. 13, 2132\u20132143. https:\/\/doi.org\/10.1109\/TAFFC.2022.3188390 (2022).","journal-title":"IEEE Transa. Affective Comput."},{"key":"39584_CR27","unstructured":"Li, J., Nie, J., Guo, D., Hong, R. & Wang, M. Emotion separation and recognition from a facial expression by generating the poker face with vision transformers. arXiv preprint arXiv:2207.11081 (2022)."},{"key":"39584_CR28","doi-asserted-by":"publisher","first-page":"14935","DOI":"10.1007\/s11042-020-08852-3","volume":"83","author":"N Hussain","year":"2024","unstructured":"Hussain, N. et al. A deep neural network and classical features based scheme for objects recognition: an application for machine inspection. Multi. Tools Appl. 83, 14935\u201314957. https:\/\/doi.org\/10.1007\/s11042-020-08852-3 (2024).","journal-title":"Multi. Tools Appl."},{"key":"39584_CR29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3427394","author":"A Ikram","year":"2024","unstructured":"Ikram, A. et al. A systematic review on fundus image-based diabetic retinopathy detection and grading: Current status and future directions. IEEE Access https:\/\/doi.org\/10.1109\/ACCESS.2024.3427394 (2024).","journal-title":"IEEE Access"},{"key":"39584_CR30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0303094","volume":"19","author":"AQ Khan","year":"2024","unstructured":"Khan, A. Q. et al. A novel fusion of genetic grey wolf optimization and kernel extreme learning machines for precise diabetic eye disease classification. Plos one 19, e0303094. https:\/\/doi.org\/10.1371\/journal.pone.0303094 (2024).","journal-title":"Plos one"},{"key":"39584_CR31","doi-asserted-by":"publisher","first-page":"7288","DOI":"10.3390\/app13127288","volume":"13","author":"AA Abdulwahid","year":"2023","unstructured":"Abdulwahid, A. A. Classification of ethnicity using efficient cnn models on morph and feret datasets based on face biometrics. Appl. Sci. 13, 7288. https:\/\/doi.org\/10.3390\/app13127288 (2023).","journal-title":"Appl. Sci."},{"key":"39584_CR32","unstructured":"Mello-Klein, C. Facebook\u00e2\u20ac\u2122s ad delivery algorithm is discriminating based on race, gender and age in photos, northeastern researchers find. https:\/\/news.northeastern.edu\/2022\/10\/25\/facebook-algorithm-discrimination\/ (2022)."},{"key":"39584_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104404","volume":"121","author":"G Sunitha","year":"2022","unstructured":"Sunitha, G. et al. Intelligent deep learning based ethnicity recognition and classification using facial images. Image Vision Comput. 121, 104404. https:\/\/doi.org\/10.1016\/j.imavis.2022.104404 (2022).","journal-title":"Image Vision Comput."},{"key":"39584_CR34","doi-asserted-by":"publisher","first-page":"4579","DOI":"10.1016\/j.jksuci.2020.11.029","volume":"34","author":"MA Ahmed","year":"2022","unstructured":"Ahmed, M. A., Choudhury, R. D. & Kashyap, K. Race estimation with deep networks. J. King Saud Univ.-Comput. Inform. Sci. 34, 4579\u20134591. https:\/\/doi.org\/10.1016\/j.jksuci.2020.11.029 (2022).","journal-title":"J. King Saud Univ.-Comput. Inform. Sci."},{"key":"39584_CR35","doi-asserted-by":"publisher","first-page":"50755","DOI":"10.1109\/ACCESS.2021.3069022","volume":"9","author":"NA Al-Humaidan","year":"2021","unstructured":"Al-Humaidan, N. A. & Prince, M. A classification of arab ethnicity based on face image using deep learning approach. IEEE Access 9, 50755\u201350766. https:\/\/doi.org\/10.1109\/ACCESS.2021.3069022 (2021).","journal-title":"IEEE Access"},{"key":"39584_CR36","doi-asserted-by":"publisher","first-page":"2605","DOI":"10.3390\/app12052605","volume":"12","author":"AJA AlBdairi","year":"2022","unstructured":"AlBdairi, A. J. A. et al. Face recognition based on deep learning and fpga for ethnicity identification. Appl. Sci. 12, 2605 (2022).","journal-title":"Appl. Sci."},{"key":"39584_CR37","doi-asserted-by":"publisher","first-page":"1413597","DOI":"10.1155\/2022\/1413597","volume":"2022","author":"S Haseena","year":"2022","unstructured":"Haseena, S. et al. Prediction of the age and gender based on human face images based on deep learning algorithm. Comput. Math. Methods Med. 2022, 1413597. https:\/\/doi.org\/10.1155\/2022\/1413597 (2022).","journal-title":"Comput. Math. Methods Med."},{"key":"39584_CR38","doi-asserted-by":"publisher","first-page":"11937","DOI":"10.1007\/s00521-023-08331-4","volume":"35","author":"M Fayyaz","year":"2023","unstructured":"Fayyaz, M. et al. Pedestrian gender classification on imbalanced and small sample datasets using deep and traditional features. Neural Comput. Appl. 35, 11937\u201311968. https:\/\/doi.org\/10.1007\/s00521-023-08331-4 (2023).","journal-title":"Neural Comput. Appl."},{"key":"39584_CR39","doi-asserted-by":"publisher","unstructured":"Sonthi, V.\u00a0K. et al. A deep learning technique for smart gender classification system. In 2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), 983\u2013987 (IEEE, 2023). https:\/\/doi.org\/10.1109\/ICACITE57410.2023.10182683.","DOI":"10.1109\/ICACITE57410.2023.10182683"},{"key":"39584_CR40","doi-asserted-by":"publisher","unstructured":"Yaman, D., Eyiokur, F.\u00a0I. & Ekenel, H.\u00a0K. Multimodal soft biometrics: combining ear and face biometrics for age and gender classification. Multimedia Tools and Applications 1\u201319 (2022). https:\/\/doi.org\/10.1007\/s11042-021-10630-8.","DOI":"10.1007\/s11042-021-10630-8"},{"key":"39584_CR41","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1109\/CVPRW.2015.7301352","volume":"42","author":"A Tunc","year":"2022","unstructured":"Tunc, A., Tasdemir, S., Koklu, M. & Cinar, A. C. Age group and gender classification using convolutional neural networks with a fuzzy logic-based filter method for noise reduction. J. Intell. & Fuzzy Systems 42, 491\u2013501. https:\/\/doi.org\/10.1109\/CVPRW.2015.7301352 (2022).","journal-title":"J. Intell. & Fuzzy Systems"},{"key":"39584_CR42","doi-asserted-by":"publisher","unstructured":"Ciobotaru, A. et al. Comparing deep learning and genetic algorithms techniques for age and gender classification. In 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 1\u20136 (IEEE, 2023). https:\/\/doi.org\/10.1109\/ICECCME57830.2023.10253422.","DOI":"10.1109\/ICECCME57830.2023.10253422"},{"key":"39584_CR43","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. Adv. Neural Inform. Processing Syst. 25, 84\u201390. https:\/\/doi.org\/10.1145\/3065386 (2012).","journal-title":"Adv. Neural Inform. Processing Syst."},{"key":"39584_CR44","doi-asserted-by":"publisher","first-page":"965","DOI":"10.2174\/2213275912666190417151247","volume":"13","author":"AM Reddy","year":"2020","unstructured":"Reddy, A. M., Krishna, V. V., Sumalatha, L. & Obulesh, A. Age classification using motif and statistical features derived on gradient facial images. Recent Adv. Comput. Sci. Commun. (Formerly: Recent Patents Comput. Sci. 13, 965\u2013976. https:\/\/doi.org\/10.2174\/2213275912666190417151247 (2020).","journal-title":"Recent Adv. Comput. Sci. Commun. (Formerly: Recent Patents Comput. Sci."},{"key":"39584_CR45","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1016\/j.neucom.2017.08.062","volume":"275","author":"M Duan","year":"2018","unstructured":"Duan, M., Li, K., Yang, C. & Li, K. A hybrid deep learning cnn-elm for age and gender classification. Neurocomputing 275, 448\u2013461. https:\/\/doi.org\/10.1016\/j.neucom.2017.08.062 (2018).","journal-title":"Neurocomputing"},{"key":"39584_CR46","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"G-B Huang","year":"2006","unstructured":"Huang, G.-B., Zhu, Q.-Y. & Siew, C.-K. Extreme learning machine: theory and applications. Neurocomputing 70, 489\u2013501. https:\/\/doi.org\/10.1016\/j.neucom.2005.12.126 (2006).","journal-title":"Neurocomputing"},{"key":"39584_CR47","doi-asserted-by":"publisher","first-page":"23311","DOI":"10.1007\/s00521-021-06012-8","volume":"35","author":"MK Chowdary","year":"2023","unstructured":"Chowdary, M. K., Nguyen, T. N. & Hemanth, D. J. Deep learning-based facial emotion recognition for human-computer interaction applications. Neural Comput. Appl. 35, 23311\u201323328. https:\/\/doi.org\/10.1007\/s00521-021-06012-8 (2023).","journal-title":"Neural Comput. Appl."},{"key":"39584_CR48","doi-asserted-by":"publisher","first-page":"24457","DOI":"10.1007\/s11042-024-20518-y","volume":"84","author":"G Meena","year":"2025","unstructured":"Meena, G., Mohbey, K. K. & Lokesh, K. Fstl-sa: Few-shot transfer learning for sentiment analysis from facial expressions. Multi. Tools Appl. 84, 24457\u201324485. https:\/\/doi.org\/10.1007\/s11042-024-20518-y (2025).","journal-title":"Multi. Tools Appl."},{"key":"39584_CR49","unstructured":"Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"39584_CR50","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1515\/jisys-2013-0010","volume":"22","author":"K Meethongjan","year":"2013","unstructured":"Meethongjan, K., Dzulkifli, M., Rehman, A., Altameem, A. & Saba, T. An intelligent fused approach for face recognition. J. Intell. Syst. 22, 197\u2013212. https:\/\/doi.org\/10.1515\/jisys-2013-0010 (2013).","journal-title":"J. Intell. Syst."},{"key":"39584_CR51","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1007\/s41095-023-0389-6","volume":"10","author":"S Deng","year":"2024","unstructured":"Deng, S. et al. Learning to compose diversified prompts for image emotion classification. Comput. Visual Media 10, 1169\u20131183. https:\/\/doi.org\/10.1007\/s41095-023-0389-6 (2024).","journal-title":"Comput. Visual Media"},{"key":"39584_CR52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3571534","author":"J Wang","year":"2025","unstructured":"Wang, J. et al. Mdkat: Multimodal decoupling with knowledge aggregation and transfer for video emotion recognition. IEEE Trans. Circuits Syst. Video Technol. https:\/\/doi.org\/10.1109\/TCSVT.2025.3571534 (2025).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"39584_CR53","doi-asserted-by":"publisher","unstructured":"Pandi, C., Adi Narayana Reddy, K., Alladi, R., Chandra Sekhar Reddy, V. & Sumithabhashini, P. Emotion and gender classification using convolution neural networks. In ICT Systems and Sustainability: Proceedings of ICT4SD 2021, Volume 1, 563\u2013573 (Springer, 2022). https:\/\/doi.org\/10.1007\/978-981-16-5987-4_57.","DOI":"10.1007\/978-981-16-5987-4_57"},{"key":"39584_CR54","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103627","volume":"88","author":"S Khellat-Kihel","year":"2022","unstructured":"Khellat-Kihel, S., Muhammad, J., Sun, Z. & Tistarelli, M. Gender and ethnicity recognition based on visual attention-driven deep architectures. J. Visual Commun. Image Representation 88, 103627. https:\/\/doi.org\/10.1016\/j.jvcir.2022.103627 (2022).","journal-title":"J. Visual Commun. Image Representation"},{"key":"39584_CR55","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105651","volume":"118","author":"P Foggia","year":"2023","unstructured":"Foggia, P., Greco, A., Saggese, A. & Vento, M. Multi-task learning on the edge for effective gender, age, ethnicity and emotion recognition. Eng. Appl. Artificial Intell. 118, 105651. https:\/\/doi.org\/10.1016\/j.engappai.2022.105651 (2023).","journal-title":"Eng. Appl. Artificial Intell."},{"key":"39584_CR56","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s40537-025-01336-x","volume":"13","author":"N AlDahoul","year":"2025","unstructured":"AlDahoul, N., Tan, M. J., Kasireddy, H. R. & Zaki, Y. Guardians of digital safety: benchmarking large language models in the fight against online toxicity. J. Big Data 13, 6. https:\/\/doi.org\/10.1186\/s40537-025-01336-x (2025).","journal-title":"J. Big Data"},{"key":"39584_CR57","unstructured":"Kuo, C.\u00a0W. et al. Neutralizing the narrative: Ai-powered debiasing of online news articles. arXiv preprint arXiv:2504.03520 (2025)."},{"key":"39584_CR58","doi-asserted-by":"publisher","unstructured":"AlDahoul, N. & Zaki, Y. Nyuad at qias shared task: Benchmarking the legal reasoning of llms in arabic islamic inheritance cases. In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, 861\u2013866 (2025). https:\/\/doi.org\/10.18653\/v1\/2025.arabicnlp-sharedtasks.118.","DOI":"10.18653\/v1\/2025.arabicnlp-sharedtasks.118"},{"key":"39584_CR59","doi-asserted-by":"publisher","unstructured":"AlDahoul, N. & Zaki, Y. Nyuad at arahealthqa shared task: Benchmarking the medical understanding and reasoning of large language models in arabic healthcare tasks. In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, 119\u2013125 (2025). https:\/\/doi.org\/10.18653\/v1\/2025.arabicnlp-sharedtasks.19.","DOI":"10.18653\/v1\/2025.arabicnlp-sharedtasks.19"},{"key":"39584_CR60","doi-asserted-by":"publisher","first-page":"7251","DOI":"10.1038\/s41598-024-77301-0","volume":"15","author":"N AlDahoul","year":"2025","unstructured":"AlDahoul, N., Hong, J., Varvello, M. & Zaki, Y. Towards a world wide web powered by generative ai. Sci. Rep. 15, 7251. https:\/\/doi.org\/10.1038\/s41598-024-77301-0 (2025).","journal-title":"Sci. Rep."},{"key":"39584_CR61","unstructured":"AlDahoul, N., Tan, M. J.\u00a0T., Kasireddy, H.\u00a0R. & Zaki, Y. Advancing content moderation: Evaluating large language models for detecting sensitive content across text, images, and videos. arXiv preprint arXiv:2411.17123 (2024)."},{"key":"39584_CR62","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-025-10774-9","volume":"15","author":"N AlDahoul","year":"2025","unstructured":"AlDahoul, N. et al. Multitasking vision language models for vehicle plate recognition with vehiclepaligemma. Sci. Rep. 15, 1\u201315. https:\/\/doi.org\/10.1038\/s41598-025-10774-9 (2025).","journal-title":"Sci. Rep."},{"key":"39584_CR63","doi-asserted-by":"publisher","unstructured":"AlDahoul, N. & Zaki, Y. Nyuad at mahed shared task: Detecting hope, hate, and emotion in arabic textual speech and multi-modal memes using large language models. In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, 575\u2013584 (2025). https:\/\/doi.org\/10.18653\/v1\/2025.arabicnlp-sharedtasks.76.","DOI":"10.18653\/v1\/2025.arabicnlp-sharedtasks.76"},{"key":"39584_CR64","unstructured":"Abdelhamed, A., Afifi, M. & Go, A. What do you see? enhancing zero-shot image classification with multimodal large language models. arXiv preprint arXiv:2405.15668 (2024)."},{"key":"39584_CR65","unstructured":"Hello gpt-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/\/ (2024)."},{"key":"39584_CR66","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)."},{"key":"39584_CR67","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.aej.2024.05.015","volume":"99","author":"B Yang","year":"2024","unstructured":"Yang, B. et al. Vision transformer-based visual language understanding of the construction process. Alexandria Eng. J. 99, 242\u2013256. https:\/\/doi.org\/10.1016\/j.aej.2024.05.015 (2024).","journal-title":"Alexandria Eng. J."},{"key":"39584_CR68","doi-asserted-by":"publisher","unstructured":"Yildirim, N. et al. Multimodal healthcare ai: identifying and designing clinically relevant vision-language applications for radiology. In Proceedings of the CHI Conference on Human Factors in Computing Systems, 1\u201322 (2024). https:\/\/doi.org\/10.1145\/3613904.3642013.","DOI":"10.1145\/3613904.3642013"},{"key":"39584_CR69","doi-asserted-by":"crossref","unstructured":"Hartsock, I. & Rasool, G. Vision-language models for medical report generation and visual question answering: A review. arXiv preprint arXiv:2403.02469 (2024).","DOI":"10.3389\/frai.2024.1430984"},{"key":"39584_CR70","doi-asserted-by":"publisher","unstructured":"Antol, S. et al. Vqa: Visual question answering. In Proceedings of the IEEE international conference on computer vision, 2425\u20132433 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.279.","DOI":"10.1109\/ICCV.2015.279"},{"key":"39584_CR71","unstructured":"Beyer, L. et al. Paligemma: A versatile 3b vlm for transfer. arXiv preprint arXiv:2407.07726 (2024)."},{"key":"39584_CR72","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"2002","unstructured":"LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proceed. IEEE 86, 2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791 (2002).","journal-title":"Proceed. IEEE"},{"key":"39584_CR73","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I. et al. Improving language understanding by generative pre-training (2018). URL https:\/\/www.mikecaptain.com\/resources\/pdf\/GPT-1.pdf."},{"key":"39584_CR74","doi-asserted-by":"publisher","unstructured":"Srivatsan, K., Naseer, M. & Nandakumar, K. Flip: Cross-domain face anti-spoofing with language guidance. In Proceedings of the IEEE\/CVF international conference on computer vision, 19685\u201319696 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01803.","DOI":"10.1109\/ICCV51070.2023.01803"},{"key":"39584_CR75","doi-asserted-by":"publisher","unstructured":"Liu, A. et al. Cfpl-fas: Class free prompt learning for generalizable face anti-spoofing. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 222\u2013232 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.00029.","DOI":"10.1109\/CVPR52733.2024.00029"},{"key":"39584_CR76","doi-asserted-by":"publisher","unstructured":"Liu, A. et al. Fm-clip: Flexible modal clip for face anti-spoofing. In Proceedings of the 32nd ACM International Conference on Multimedia, 8228\u20138237 (2024). https:\/\/doi.org\/10.1145\/3664647.3680856.","DOI":"10.1145\/3664647.3680856"},{"key":"39584_CR77","doi-asserted-by":"publisher","unstructured":"Lin, K.-H., Tseng, Y.-W., Huang, K.-Y., Wu, J.-C. & Cheng, W.-H. Instructflip: Exploring unified vision-language model for face anti-spoofing. In Proceedings of the 33rd ACM International Conference on Multimedia, 2987\u20132996 (2025). https:\/\/doi.org\/10.1145\/3746027.3754939.","DOI":"10.1145\/3746027.3754939"},{"key":"39584_CR78","unstructured":"Gemini Team, G. Gemini 1.5 technical report. https:\/\/storage.googleapis.com\/deepmind-media\/gemini\/gemini_v1_5_report.pdf (2024)."},{"key":"39584_CR79","unstructured":"Introducing gemini 1.5, google\u00e2\u20ac\u2122s next-generation ai model. https:\/\/blog.google\/technology\/ai\/google-gemini-next-generation-model-february-2024\/#architecture (2024)."},{"key":"39584_CR80","unstructured":"Gpt-4o: The comprehensive guide and explanation. https:\/\/blog.roboflow.com\/gpt-4o-vision-use-cases\/ (2024)."},{"key":"39584_CR81","unstructured":"Llava: Large language and vision assistant explained. https:\/\/encord.com\/blog\/llava-large-language-vision-assistant\/ (2024)."},{"key":"39584_CR82","unstructured":"Liu, H. et al. Llava-next: Improved reasoning, ocr, and world knowledge (2024). URL https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/."},{"key":"39584_CR83","unstructured":"Dang, P. Multimodal (visual and language) understanding with llava-next. https:\/\/rocm.blogs.amd.com\/artificial-intelligence\/llava-next\/README.html (2023)."},{"key":"39584_CR84","unstructured":"Zhu, H. et al. Harnessing large vision and language models in agriculture: A review. arXiv preprint arXiv:2407.19679 (2024)."},{"key":"39584_CR85","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B. et al. Yfcc100m: The new data in multimedia research. Commun. ACM 59, 64\u201373 (2016).","journal-title":"Commun. ACM"},{"key":"39584_CR86","unstructured":"Meta. Llama 3.2: Revolutionizing edge ai and vision with open, customizable models. https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices\/ (2024)."},{"key":"39584_CR87","unstructured":"Hugging face. https:\/\/huggingface.co\/."},{"key":"39584_CR88","unstructured":"AWS. Amazon rekognition. https:\/\/docs.aws.amazon.com\/rekognition\/latest\/APIReference\/API_AgeRange.html."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39584-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39584-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39584-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T09:45:39Z","timestamp":1774604739000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39584-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,23]]},"references-count":88,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["39584"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-39584-3","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,23]]},"assertion":[{"value":"12 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10246"}}