{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T13:06:15Z","timestamp":1775653575046,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["Mach. Intell. Res."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s11633-025-1601-1","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T10:35:09Z","timestamp":1775644509000},"page":"396-408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unveiling Hidden Psychological States: Synergistic Fusion of Amplified Color and Motion from Video"],"prefix":"10.1007","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5577-2769","authenticated-orcid":false,"given":"Yiwei","family":"Ru","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7905-2860","authenticated-orcid":false,"given":"Qi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongji","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijia","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3433-8435","authenticated-orcid":false,"given":"Zhaofeng","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-9935","authenticated-orcid":false,"given":"Zhenan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"1601_CR1","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199942237.001.0001","volume-title":"The Oxford Handbook of Affective Computing","author":"R A Calvo","year":"2015","unstructured":"R. A. Calvo, S. D\u2019Mello, J. Gratch, A. Kappas. The Oxford Handbook of Affective Computing, Oxford, UK: Oxford University Press, 2015."},{"key":"1601_CR2","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.inffus.2017.02.003","volume":"37","author":"S Poria","year":"2017","unstructured":"S. Poria, E. Cambria, R. Bajpai, A. Hussain. A review of affective computing: From unimodal analysis to multimodal fusion. Information Fusion, vol. 37, pp. 98\u2013125, 2017. DOI: https:\/\/doi.org\/10.1016\/j.inffus.2017.02.003.","journal-title":"Information Fusion"},{"issue":"8","key":"1601_CR3","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1016\/j.medengphy.2006.09.006","volume":"29","author":"C Takano","year":"2007","unstructured":"C. Takano, Y. Ohta. Heart rate measurement based on a time-lapse image. Medical Engineering & Physics, vol. 29, no. 8, pp. 853\u2013857, 2007. DOI: https:\/\/doi.org\/10.1016\/j.medeng-phy.2006.09.006.","journal-title":"Medical Engineering & Physics"},{"key":"1601_CR4","doi-asserted-by":"publisher","unstructured":"L. Zhao, C. Liang, Y. Huang, G. Zhou, Y. Xiao, N. Ji, Y. T. Zhang, N. Zhao. Emerging sensing and modeling technologies for wearable and cuffless blood pressure monitoring. NPJ Digital Medicine, vol. 6, no. 1, Article number 93, 2023. DOI: https:\/\/doi.org\/10.1038\/s41746-023-00835-6.","DOI":"10.1038\/s41746-023-00835-6"},{"key":"1601_CR5","doi-asserted-by":"publisher","unstructured":"H. Y. Wu, M. Rubinstein, E. Shih, J. Guttag, F. Durand, W. Freeman. Eulerian video magnification for revealing subtle changes in the world. ACM Transactions on Graphics (TOG), vol. 31, no. 4, Article number 65, 2012. DOI: https:\/\/doi.org\/10.1145\/2185520.2185561.","DOI":"10.1145\/2185520.2185561"},{"issue":"1","key":"1601_CR6","doi-asserted-by":"publisher","first-page":"49","DOI":"10.4103\/hm.hm_59_22","volume":"7","author":"C J Lavie","year":"2023","unstructured":"C. J. Lavie, I. Zhang, D. Yang, M. Liu. Improving fitness through exercise will improve our heart and mind. Heart and Mind, vol. 7, no. 1, pp. 49\u201351, 2023. DOI: https:\/\/doi.org\/10.4103\/hm.hm_59_22.","journal-title":"Heart and Mind"},{"issue":"3","key":"1601_CR7","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.tins.2011.12.001","volume":"35","author":"K E Cullen","year":"2012","unstructured":"K. E. Cullen. The vestibular system: Multimodal integration and encoding of self-motion for motor control. Trends in Neurosciences, vol. 35, no. 3, pp. 185\u2013196, 2012. DOI: https:\/\/doi.org\/10.1016\/j.tins.2011.12.001.","journal-title":"Trends in Neurosciences"},{"issue":"1","key":"1601_CR8","doi-asserted-by":"publisher","first-page":"18","DOI":"10.4103\/hm.hm_33_22","volume":"7","author":"D Popovic","year":"2023","unstructured":"D. Popovic, C. J. Lavie. Stress, cardiovascular diseases and exercise-A narrative review. Heart and Mind, vol. 7, no. 1, pp. 18\u201324, 2023. DOI: https:\/\/doi.org\/10.4103\/hm.hm_33_22.","journal-title":"Heart and Mind"},{"key":"1601_CR9","doi-asserted-by":"publisher","unstructured":"S. Cauzzo, K. Singh, M. Stauder, M. G. Garc\u00eda-Gomar, N. Vanello, C. Passino, J. Staab, I. Indovina, M. Bianciardi. Functional connectome of brainstem nuclei involved in autonomic, limbic, pain and sensory processing in living humans from 7 tesla resting state FMRI. Neuroimage, vol. 250, Article number 118925, 2022. DOI: https:\/\/doi.org\/10.1016\/j.neuroimage.2022.118925.","DOI":"10.1016\/j.neuroimage.2022.118925"},{"issue":"1","key":"1601_CR10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.4103\/hm.hm_50_22","volume":"7","author":"J L Taylor","year":"2023","unstructured":"J. L. Taylor. Exercise and the brain in cardiovascular disease: A narrative review. Heart and Mind, vol. 7, no. 1, pp. 5\u201312, 2023. DOI: https:\/\/doi.org\/10.4103\/hm.hm_50_22.","journal-title":"Heart and Mind"},{"key":"1601_CR11","doi-asserted-by":"publisher","first-page":"5935","DOI":"10.1145\/3581783.3611754","volume-title":"Proceedings of the 31st ACM International Conference on Multimedia","author":"Y Ru","year":"2023","unstructured":"Y. Ru, P. Li, M. Sun, Y. Wang, K. Zhang, Q. Li, Z. He, Z. Sun. Sensing micro-motion human patterns using multimodal mmRadar and video signal for affective and psychological intelligence. In Proceedings of the 31st ACM International Conference on Multimedia, Ottawa, Canada, pp. 5935\u20135946, 2023. DOI: https:\/\/doi.org\/10.1145\/3581783.3611754."},{"issue":"26","key":"1601_CR12","doi-asserted-by":"publisher","first-page":"21434","DOI":"10.1364\/OE.16.021434","volume":"16","author":"W Verkruysse","year":"2008","unstructured":"W. Verkruysse, L. O. Svaasand, J. S. Nelson. Remote plethysmographic imaging using ambient light. Optics Express, vol. 16, no. 26, pp. 21434\u201321445, 2008. DOI: https:\/\/doi.org\/10.1364\/OE.16.021434.","journal-title":"Optics Express"},{"issue":"1","key":"1601_CR13","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TBME.2010.2086456","volume":"58","author":"M Z Poh","year":"2011","unstructured":"M. Z. Poh, D. J. McDuff, R. W. Picard. Advancements in noncontact, multiparameter physiological measurements using a webcam. IEEE Transactions on Biomedical Engineering, vol. 58, no. 1, pp. 7\u201311, 2011. DOI: https:\/\/doi.org\/10.1109\/TBME.2010.2086456.","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"1601_CR14","first-page":"405","volume-title":"Proceedings of Federated Conference on Computer Science and Information Systems","author":"M Lewandowska","year":"2011","unstructured":"M. Lewandowska, J. Ruminski, T. Kocejko, J. Nowak. Measuring pulse rate with a webcam \u2013 A non-contact method for evaluating cardiac activity. In Proceedings of Federated Conference on Computer Science and Information Systems, IEEE, Szczecin, Poland, pp. 405\u2013410, 2011."},{"issue":"10","key":"1601_CR15","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1109\/TBME.2013.2266196","volume":"60","author":"G de Haan","year":"2013","unstructured":"G. de Haan, V. Jeanne. Robust pulse rate from chrominance-based rPPG. IEEE Transactions on Biomedical Engineering, vol. 60, no. 10, pp. 2878\u20132886, 2013. DOI: https:\/\/doi.org\/10.1109\/TBME.2013.2266196.","journal-title":"IEEE Transactions on Biomedical Engineering"},{"issue":"7","key":"1601_CR16","doi-asserted-by":"publisher","first-page":"1479","DOI":"10.1109\/TBME.2016.2609282","volume":"64","author":"W Wang","year":"2017","unstructured":"W. Wang, A. C. den Brinker, S. Stuijk, G. de Haan. Algorithmic principles of remote PPG. IEEE Transactions on Biomedical Engineering, vol. 64, no. 7, pp. 1479\u20131491, 2017. DOI: https:\/\/doi.org\/10.1109\/TBME.2016.2609282.","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"1601_CR17","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1007\/978-3-030-01216-8_22","volume-title":"Proceedings of the 15th European Conference on Computer Vision","author":"W Chen","year":"2018","unstructured":"W. Chen, D. McDuff. DeepPhys: Video-based physiological measurement using convolutional attention networks. In Proceedings of the 15th European Conference on Computer Vision, Springer, Munich, Germany, pp. 356\u2013373, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01216-8_22."},{"key":"1601_CR18","doi-asserted-by":"publisher","first-page":"1380","DOI":"10.1109\/CVPRW.2018.00177","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"C Zhao","year":"2018","unstructured":"C. Zhao, C. L. Lin, W. Chen, Z. Li. A novel framework for remote photoplethysmography pulse extraction on compressed videos. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, IEEE, Salt Lake City, USA, pp. 1380\u2013138009, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPRW.2018.00177."},{"issue":"6","key":"1601_CR19","doi-asserted-by":"publisher","first-page":"3678","DOI":"10.1021\/acs.jctc.9b00181","volume":"15","author":"O T Unke","year":"2019","unstructured":"O. T. Unke, M. Meuwly. Physnet: A neural network for predicting energies, forces, dipole moments, and partial charges. Journal of Chemical Theory and Computation, vol. 15, no. 6, pp. 3678\u20133693, 2019. DOI: https:\/\/doi.org\/10.1021\/acs.jctc.9b00181.","journal-title":"Journal of Chemical Theory and Computation"},{"key":"1601_CR20","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing System","author":"X Liu","year":"2020","unstructured":"X. Liu, J. Fromm, S. Patel, D. McDuff. Multi-task temporal shift attention networks for on-device contactless vitals measurement. In Proceedings of the 34th International Conference on Neural Information Processing System, Vancouver, Canada, Article number 1627, 2020."},{"key":"1601_CR21","doi-asserted-by":"publisher","first-page":"4997","DOI":"10.1109\/WACV56688.2023.00498","volume-title":"Proceedings of IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"X Liu","year":"2023","unstructured":"X. Liu, B. Hill, Z. Jiang, S. Patel, D. McDuff. Efficient-Phys: Enabling simple, fast and accurate camera-based cardiac measurement. In Proceedings of IEEE\/CVF Winter Conference on Applications of Computer Vision, IEEE, Waikoloa, USA, pp. 4997\u20135006, 2023. DOI: https:\/\/doi.org\/10.1109\/WACV56688.2023.00498."},{"key":"1601_CR22","doi-asserted-by":"publisher","first-page":"4176","DOI":"10.1109\/CVPR52688.2022.00415","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Yu","year":"2022","unstructured":"Z. Yu, Y. Shen, J. Shi, H. Zhao, P. Torr, G. Zhao. Phys-Former: Facial video-based physiological measurement with temporal difference transformer. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, New Orleans, USA, pp. 4176\u20134186, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.00415."},{"issue":"4","key":"1601_CR23","doi-asserted-by":"publisher","first-page":"195","DOI":"10.15406\/ijbsbe.2018.04.00125","volume":"4","author":"D Castaneda","year":"2018","unstructured":"D. Castaneda, A. Esparza, M. Ghamari, C. Soltanpur, H. Nazeran. A review on wearable photoplethysmography sensors and their potential future applications in health care. International Journal of Biosensors & Bioelectronics, vol. 4, no. 4, pp. 195\u2013202, 2018. DOI: https:\/\/doi.org\/10.15406\/ijbsbe.2018.04.00125.","journal-title":"International Journal of Biosensors & Bioelectronics"},{"key":"1601_CR24","doi-asserted-by":"publisher","unstructured":"A. S. Salim, A. S. M. Khidhir. A comprehensive review of rPPG methods for heart rate estimation. Open Access Library Journal, vol. 11, Article number e12482, 2024. DOI: https:\/\/doi.org\/10.4236\/oalib.1112482.","DOI":"10.4236\/oalib.1112482"},{"issue":"6","key":"1601_CR25","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1088\/1361-6579\/aa6d02","volume":"38","author":"W Wang","year":"2017","unstructured":"W. Wang, A. C. den Brinker, S. Stuijk, G. de Haan. Robust heart rate from fitness videos. Physiological Measurement, vol. 38, no. 6, pp. 1023\u20131044, 2017. DOI: https:\/\/doi.org\/10.1088\/1361-6579\/aa6d02.","journal-title":"Physiological Measurement"},{"key":"1601_CR26","first-page":"46","volume":"224","author":"H Rahman","year":"2016","unstructured":"H. Rahman, M. U. Ahmed, S. Begum. Non-contact heart rate monitoring using lab color space. Studies in Health Technology and Informatics, vol. 224, pp. 46\u201353, 2016","journal-title":"Studies in Health Technology and Informatics"},{"issue":"5","key":"1601_CR27","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1109\/TBME.2015.2390261","volume":"62","author":"M van Gastel","year":"2015","unstructured":"M. van Gastel, S. Stuijk, G. de Haan. Motion robust remote-PPG in infrared. IEEE Transactions on Biomedical Engineering, vol. 62, no. 5, pp. 1425\u20131433, 2015. DOI: https:\/\/doi.org\/10.1109\/TBME.2015.2390261.","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"1601_CR28","doi-asserted-by":"publisher","unstructured":"N. Wadhwa, M. Rubinstein, F. Durand, W. T. Freeman. Phase-based video motion processing. ACM Transactions on Graphics (ToG), vol. 32, no. 4, Article number 80, 2013. DOI: https:\/\/doi.org\/10.1145\/2461912.2461966.","DOI":"10.1145\/2461912.2461966"},{"key":"1601_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICCPHOT.2014.6831820","volume-title":"Proceedings of IEEE International Conference on Computational Photography","author":"N Wadhwa","year":"2014","unstructured":"N. Wadhwa, M. Rubinstein, F. Durand, W. T. Freeman. Riesz pyramids for fast phase-based video magnification. In Proceedings of IEEE International Conference on Computational Photography, Santa Clara, USA, pp. 1\u201310, 2014. DOI: https:\/\/doi.org\/10.1109\/ICCPHOT.2014.6831820."},{"key":"1601_CR30","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/978-3-030-01225-039","volume-title":"Proceedings of the 15th European Conference on Computer Vision","author":"T H Oh","year":"2018","unstructured":"T. H. Oh, R. Jaroensri, C. Kim, M. Elgharib, F. Durand, W. T. Freeman, W. Matusik. Learning-based video motion magnification. In Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, pp. 663\u2013679, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01225-039."},{"key":"1601_CR31","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/CVPR.2017.61","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"Y Zhang","year":"2017","unstructured":"Y. Zhang, S. L. Pintea, J. C. van Gemert. Video acceleration magnification. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, USA, pp. 502\u2013510, 2017. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.61."},{"key":"1601_CR32","doi-asserted-by":"publisher","unstructured":"R. Lado-Roig\u00e9, M. A. P\u00e9rez. STB-VMM: Swin transformer based video motion magnification. Knowledge-Based Systems, vol. 269, Article number 110493, 2023. DOI: https:\/\/doi.org\/10.1016\/j.knosys.2023.110493.","DOI":"10.1016\/j.knosys.2023.110493"},{"issue":"2","key":"1601_CR33","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"M. Everingham, L. van Gool, C. K. I. Williams, J. Winn, A. Zisserman. The PASCAL visual object classes (VOC) challenge. International Journal of Computer Vision, vol. 88, no. 2, pp. 303\u2013338, 2010. DOI: https:\/\/doi.org\/10.1007\/s11263-009-0275-4.","journal-title":"International Journal of Computer Vision"},{"key":"1601_CR34","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Proceedings of the 13th European Conference on Computer Vision","author":"T Y Lin","year":"2014","unstructured":"T. Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, C. L. Zitnick. Microsoft COCO: Common objects in context. In Proceedings of the 13th European Conference on Computer Vision, Zurich, Switzerland, pp. 740\u2013755, 2014. DOI: https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48."},{"key":"1601_CR35","doi-asserted-by":"publisher","first-page":"103976","DOI":"10.1109\/ACCESS.2024.3430850","volume":"12","author":"S Kalateh","year":"2024","unstructured":"S. Kalateh, L. A. Estrada-Jimenez, S. Nikghadam-Hojjati, J. Barata. A systematic review on multimodal emotion recognition: Building blocks, current state, applications, and challenges. IEEE Access, vol. 12, pp. 103976\u2013104019, 2024. DOI: https:\/\/doi.org\/10.1109\/ACCESS.2024.3430850.","journal-title":"IEEE Access"},{"key":"1601_CR36","doi-asserted-by":"publisher","first-page":"5089","DOI":"10.1109\/ICASSP.2018.8462677","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","author":"P Tzirakis","year":"2018","unstructured":"P. Tzirakis, J. Zhang, B. W. Schuller. End-to-end speech emotion recognition using deep neural networks. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Canada, 5089\u20135093, 2018. DOI: https:\/\/doi.org\/10.1109\/ICASSP.2018.8462677."},{"key":"1601_CR37","doi-asserted-by":"publisher","unstructured":"M. Z. Hossain, F. Sohel, M. F. Shiratuddin, H. Laga. A comprehensive survey of deep learning for image captioning. ACM Computing Surveys (CSUR), vol. 51, no. 6, Article number 118, 2019. DOI: https:\/\/doi.org\/10.1145\/3295748.","DOI":"10.1145\/3295748"},{"issue":"1\u20132","key":"1601_CR38","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.cviu.2006.10.019","volume":"108","author":"A Jaimes","year":"2007","unstructured":"A. Jaimes, N. Sebe. Multimodal human-computer interaction: A survey. Computer Vision and Image Understanding, vol. 108, no. 1\u20132, pp. 116\u2013134, 2007. DOI: https:\/\/doi.org\/10.1016\/j.cviu.2006.10.019.","journal-title":"Computer Vision and Image Understanding"},{"issue":"1","key":"1601_CR39","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/T-AFFC.2011.15","volume":"3","author":"S Koelstra","year":"2012","unstructured":"S. Koelstra, C. Muhl, M. Soleymani, J. S. Lee, A. Yazdani, T. Ebrahimi, T. Pun, A. Nijholt, I. Patras. DEAP: A database for emotion analysis; Using physiological signals. IEEE Transactions on Affective Computing, vol. 3, no. 1, pp. 18\u201331, 2012. DOI: https:\/\/doi.org\/10.1109\/T-AFFC.2011.15.","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"1","key":"1601_CR40","doi-asserted-by":"publisher","first-page":"47","DOI":"10.32604\/csse.2021.015222","volume":"37","author":"M M A Al Qudah","year":"2021","unstructured":"M. M. A. Al Qudah, A. S. A. Mohamed, S. L. Lutfi. Affective state recognition using thermal-based imaging: A survey. Computer Systems Science and Engineering, vol. 37, no. 1, pp. 47\u201362, 2021. DOI: https:\/\/doi.org\/10.32604\/csse.2021.015222.","journal-title":"Computer Systems Science and Engineering"},{"key":"1601_CR41","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.18653\/v1\/D17-1115","volume-title":"Proceedings of Conference on Empirical Methods in Natural Language Processing","author":"A Zadeh","year":"2017","unstructured":"A. Zadeh, M. Chen, S. Poria, E. Cambria, L. P. Morency. Tensor fusion network for multimodal sentiment analysis. In Proceedings of Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, pp. 1103\u20131114, 2017. DOI: https:\/\/doi.org\/10.18653\/v1\/D17-1115."},{"key":"1601_CR42","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1145\/3474085.3475460","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia","author":"Z Shao","year":"2021","unstructured":"Z. Shao, S. Song, S. Jaiswal, L. Shen, M. Valstar, H. Gunes. Personality recognition by modelling person-specific cognitive processes using graph representation. In Proceedings of the 29th ACM International Conference on Multimedia, pp. 357\u2013366, 2021. DOI: https:\/\/doi.org\/10.1145\/3474085.3475460."},{"key":"1601_CR43","first-page":"6000","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"A Vaswani","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, I. Polosukhin. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, pp. 6000\u20136010, 2017."},{"issue":"2","key":"1601_CR44","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltrusaitis","year":"2019","unstructured":"T. Baltrusaitis, C. Ahuja, L. P. Morency. Multimodal machine learning: A survey and taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 2, pp. 423\u2013443, 2019. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2018.2798607.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1601_CR45","doi-asserted-by":"publisher","first-page":"13914","DOI":"10.1109\/CVPR52729.2023.01337","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Singh","year":"2023","unstructured":"J. Singh, S. Murala, G. S. R. Kosuru. Multi domain learning for motion magnification. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Vancouver, Canada, pp. 13914\u201313923, 2023. DOI: https:\/\/doi.org\/10.1109\/CVPR52729.2023.01337."},{"key":"1601_CR46","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"T Xiao","year":"2021","unstructured":"T. Xiao, M. Singh, E. Mintun, T. Darrell, P. Dollar, R. Girshick. Early convolutions help transformers see better. In Proceedings of the 35th International Conference on Neural Information Processing Systems, Article number 2325, 2021."},{"key":"1601_CR47","first-page":"894","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"M Cuturi","year":"2017","unstructured":"M. Cuturi, M. Blondel. Soft-DTW: A differentiable loss function for time-series. In Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, pp. 894\u2013903, 2017."},{"key":"1601_CR48","doi-asserted-by":"publisher","first-page":"6201","DOI":"10.1109\/ICCV.2019.00630","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"C Feichtenhofer","year":"2019","unstructured":"C. Feichtenhofer, H. Fan, J. Malik, K. He. SlowFast networks for video recognition. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Seoul, Republic of Korea, pp. 6201\u20136210, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00630."},{"key":"1601_CR49","doi-asserted-by":"publisher","first-page":"4794","DOI":"10.1109\/CVPR52688.2022.00476","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Li","year":"2022","unstructured":"Y. Li, C. Y. Wu, H. Fan, K. Mangalam, B. Xiong, J. Malik, C. Feichtenhofer. MViTv2: Improved multiscale vision transformers for classification and detection. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, New Orleans, USA, pp. 4794\u20134804, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.00476."}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-025-1601-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-025-1601-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-025-1601-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T12:03:21Z","timestamp":1775649801000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-025-1601-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["1601"],"URL":"https:\/\/doi.org\/10.1007\/s11633-025-1601-1","relation":{},"ISSN":["2731-538X","2731-5398"],"issn-type":[{"value":"2731-538X","type":"print"},{"value":"2731-5398","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"27 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declared that they have no conflicts of interest to this work.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations of conflict of interest"}}]}}