{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T23:06:34Z","timestamp":1772060794425,"version":"3.50.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:00:00Z","timestamp":1771977600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:00:00Z","timestamp":1771977600000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-026-21343-1","type":"journal-article","created":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T22:54:09Z","timestamp":1772060049000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An effective multi-modal fusion based emotional recognition using cross attention auto encoded puma graph embedding model"],"prefix":"10.1007","volume":"85","author":[{"given":"Ajay","family":"Kapase","sequence":"first","affiliation":[]},{"given":"Nilesh","family":"Uke","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,25]]},"reference":[{"key":"21343_CR1","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1007\/s12559-023-10171-2","volume":"16","author":"T Dhara","year":"2024","unstructured":"Dhara T, Singh PK, Mahmud M (2024) A fuzzy ensemble-based deep learning model for EEG-based emotion recognition. Cogn Comput 16:1364\u20131378","journal-title":"Cogn Comput"},{"key":"21343_CR2","doi-asserted-by":"publisher","first-page":"94281","DOI":"10.1109\/ACCESS.2023.3310428","volume":"11","author":"HM Shahzad","year":"2023","unstructured":"Shahzad HM, Bhatti SM, Jaffar A, Rashid M, Akram S (2023) Multi-modal CNN features fusion for emotion recognition: a modified xception model. IEEE Access 11:94281\u201394289","journal-title":"IEEE Access"},{"key":"21343_CR3","doi-asserted-by":"crossref","unstructured":"Akhtar MS, Chauhan DS, Ghosal D, Poria S, Ekbal A, Bhattacharyya P (2019) Multi-task learning for multi-modal emotion recognition and sentiment analysis. https:\/\/arxiv.org\/abs\/1905.05812.","DOI":"10.18653\/v1\/N19-1034"},{"key":"21343_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106764","volume":"181","author":"C Fu","year":"2025","unstructured":"Fu C, Qian F, Su K, Su Y, Wang Z, Shi J, Liu Z, Liu C, Ishi CT (2025) Himul-LGG: a hierarchical decision fusion-based local\u2013global graph neural network for multimodal emotion recognition in conversation. Neural Netw 181:106764","journal-title":"Neural Netw"},{"key":"21343_CR5","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1109\/TNSRE.2023.3253866","volume":"31","author":"M Wu","year":"2023","unstructured":"Wu M, Teng W, Fan C, Pei S, Li P, Lv Z (2023) An investigation of olfactory-enhanced video on EEG-based emotion recognition. IEEE Trans Neural Syst Rehabil Eng 31:1602\u20131613","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"21343_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121419","volume":"237","author":"J Wei","year":"2024","unstructured":"Wei J, Hu G, Yang X, Luu AT, Dong Y (2024) Learning facial expression and body gesture visual information for video emotion recognition. Expert Syst Appl 237:121419","journal-title":"Expert Syst Appl"},{"key":"21343_CR7","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/TBC.2022.3215245","volume":"69","author":"Q Wei","year":"2022","unstructured":"Wei Q, Huang X, Zhang Y (2022) Fv2es: a fully end2end multimodal system for fast yet effective video emotion recognition inference. IEEE Trans Broadcast 69:10\u201320","journal-title":"IEEE Trans Broadcast"},{"key":"21343_CR8","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1109\/TCSS.2022.3228649","volume":"11","author":"Y Khurana","year":"2022","unstructured":"Khurana Y, Gupta S, Sathyaraj R, Raja SP (2022) Robinnet: a multimodal speech emotion recognition system with speaker recognition for social interactions. IEEE Trans Comput Soc Syst 11:478\u2013487","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"21343_CR9","doi-asserted-by":"publisher","first-page":"2863","DOI":"10.1109\/TNNLS.2022.3192469","volume":"35","author":"Z Lian","year":"2022","unstructured":"Lian Z, Liu B, Tao J (2022) PIRNet: personality-enhanced iterative refinement network for emotion recognition in conversation. IEEE Trans Neural Netw Learn Syst 35:2863\u20132874","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"21343_CR10","doi-asserted-by":"publisher","first-page":"14742","DOI":"10.1109\/ACCESS.2023.3244390","volume":"11","author":"H-D Le","year":"2023","unstructured":"Le H-D, Lee G-S, Kim S-H, Kim S, Yang H-J (2023) Multi-label multimodal emotion recognition with transformer-based fusion and emotion-level representation learning. IEEE Access 11:14742\u201314751","journal-title":"IEEE Access"},{"key":"21343_CR11","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/9645611","volume":"2023","author":"X Liu","year":"2023","unstructured":"Liu X, Xu Z, Huang K (2023) Multimodal emotion recognition based on cascaded multichannel and hierarchical fusion. Comput Intell Neurosci 2023:9645611","journal-title":"Comput Intell Neurosci"},{"key":"21343_CR12","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1109\/TPAMI.2023.3325770","volume":"46","author":"MK Tellamekala","year":"2023","unstructured":"Tellamekala MK, Amiriparian S, Schuller BW, Andr\u00e9 E, Giesbrecht T, Valstar M (2023) Cold fusion: calibrated and ordinal latent distribution fusion for uncertainty-aware multimodal emotion recognition. IEEE Trans Pattern Anal Mach Intell 46:805\u2013822","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"21343_CR13","doi-asserted-by":"publisher","first-page":"5475","DOI":"10.3390\/s23125475","volume":"23","author":"D Mamieva","year":"2023","unstructured":"Mamieva D, Abdusalomov AB, Kutlimuratov A, Muminov B, Whangbo TK (2023) Multimodal emotion detection via attention-based fusion of extracted facial and speech features. Sensors 23:5475","journal-title":"Sensors"},{"key":"21343_CR14","doi-asserted-by":"publisher","first-page":"14324","DOI":"10.1109\/ACCESS.2024.3356185","volume":"12","author":"S Hong","year":"2024","unstructured":"Hong S, Kang H, Cho H (2024) Cross-modal dynamic transfer learning for multimodal emotion recognition. IEEE Access 12:14324\u201314333","journal-title":"IEEE Access"},{"key":"21343_CR15","first-page":"2689","volume":"78","author":"F Harby","year":"2024","unstructured":"Harby F, Alohali M, Thaljaoui A, Talaat AS (2024) Exploring sequential feature selection in deep Bi-LSTM models for speech emotion recognition. Comput Mater Contin 78:2689\u20132719","journal-title":"Comput Mater Contin"},{"key":"21343_CR16","volume":"113","author":"DA Moreno-Galv\u00e1n","year":"2025","unstructured":"Moreno-Galv\u00e1n DA, L\u00f3pez-Santill\u00e1n R, Gonz\u00e1lez-Gurrola LC, Montes-Y-G\u00f3mez M, S\u00e1nchez-Vega F, L\u00f3pez-Monroy AP (2025) Automatic movie genre classification & emotion recognition via a biprojection multimodal transformer. Infus 113:102641","journal-title":"Infus"},{"key":"21343_CR17","doi-asserted-by":"publisher","first-page":"22245","DOI":"10.1007\/s00521-024-10240-z","volume":"36","author":"IA Castiblanco Jimenez","year":"2024","unstructured":"Castiblanco Jimenez IA, Olivetti EC, Vezzetti E, Moos S, Celeghin A, Marcolin F (2024) Effective affective EEG-based indicators in emotion-evoking VR environments: evidence from machine learning. Neural Comput Appl 36:22245\u201322263","journal-title":"Neural Comput Appl"},{"key":"21343_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130185","volume":"638","author":"F Marcolin","year":"2025","unstructured":"Marcolin F, Olivetti EC, Jimenez IA, Passavanti G, Moos S, Vezzetti E, Celeghin A (2025) Stress assessment with EEG and machine learning in affective VR environments. Neurocomputing 638:130185","journal-title":"Neurocomputing"},{"key":"21343_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-024-00347-3","volume":"13","author":"J Zhu","year":"2024","unstructured":"Zhu J, Wang S, Wang T, Huang J, Zhu X (2024) Multi-modal emotion recognition using tensor decomposition fusion and self-supervised multi-tasking. Int J Multimed Inf Retr 13:39","journal-title":"Int J Multimed Inf Retr"},{"key":"21343_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-2444-y","volume":"18","author":"Z Fu","year":"2024","unstructured":"Fu Z, Liu F, Xu Q, Fu X, Qi J (2024) LMR-CBT: learning modality-fused representations with CB-Transformer for multimodal emotion recognition from unaligned multimodal sequences. Front Comput Sci 18:184314","journal-title":"Front Comput Sci"},{"key":"21343_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111126","volume":"283","author":"X Li","year":"2024","unstructured":"Li X, Liu J, Xie Y, Gong P, Zhang X, He H (2024) Magdra: a multi-modal attention graph network with dynamic routing-by-agreement for multi-label emotion recognition. Knowl-Based Syst 283:111126","journal-title":"Knowl-Based Syst"},{"key":"21343_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108348","volume":"133","author":"G Yin","year":"2024","unstructured":"Yin G, Liu Y, Liu T, Zhang H, Fang F, Tang C, Jiang L (2024) Token-disentangling mutual transformer for multimodal emotion recognition. Eng Appl Artif Intell 133:108348","journal-title":"Eng Appl Artif Intell"},{"key":"21343_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121515","volume":"690","author":"X-C Li","year":"2025","unstructured":"Li X-C, Zhang F, Hua Q, Dong C-R (2025) A deep spatiotemporal interaction network for multimodal sentimental analysis and emotion recognition. Inf Sci 690:121515","journal-title":"Inf Sci"},{"key":"21343_CR24","doi-asserted-by":"publisher","first-page":"2415","DOI":"10.1109\/TAFFC.2022.3141237","volume":"14","author":"Z Lian","year":"2022","unstructured":"Lian Z, Liu B, Tao J (2022) Smin: semi-supervised multi-modal interaction network for conversational emotion recognition. IEEE Trans Affect Comput 14:2415\u20132429","journal-title":"IEEE Trans Affect Comput"},{"key":"21343_CR25","doi-asserted-by":"publisher","DOI":"10.3390\/app14062252","volume":"14","author":"HF Al-Saadawi","year":"2024","unstructured":"Al-Saadawi HF, Das R (2024) Ter-ca-WGNN: trimodel emotion recognition using cumulative attribute-weighted graph neural network. Appl Sci 14:2252","journal-title":"Appl Sci"},{"key":"21343_CR26","doi-asserted-by":"publisher","DOI":"10.1155\/2024\/7499554","author":"HR Banjar","year":"2024","unstructured":"Banjar HR, Alsefri L, Alshomrani A, Hamdhy M, Alahmari S, Sharaf S (2024) Activating the mobile user interface with a rule-based chatbot and EEG-based emotion recognition to aid in coping with negative emotions. Human Behavior and Emerging Technologies. https:\/\/doi.org\/10.1155\/2024\/7499554","journal-title":"Human Behavior and Emerging Technologies"},{"key":"21343_CR27","doi-asserted-by":"crossref","unstructured":"Ryumina E, Markitantov M, Ryumin D, Kaya H, Karpov A (2024) Audio-visual compound expression recognition method based on late modality fusion and rule-based decision. https:\/\/arxiv.org\/abs\/2403.12687.","DOI":"10.1109\/CVPRW63382.2024.00478"},{"key":"21343_CR28","doi-asserted-by":"publisher","DOI":"10.1155\/int\/7184626","author":"P Wu","year":"2025","unstructured":"Wu P, Lin J, Ma Z, Li H (2025) Enhancing interpretability: a hierarchical belief rule-based (HBRB) method for assessing multimodal social media credibility. Int J Intell Syst. https:\/\/doi.org\/10.1155\/int\/7184626","journal-title":"Int J Intell Syst"},{"key":"21343_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-024-03055-1","volume":"5","author":"MS Mukta","year":"2024","unstructured":"Mukta MS, Ahmed J, Raiaan MA, Fahad NM, Islam MN, Imtiaz N, Islam MA, Ali ME, Azam S (2024) Behavior based group recommendation from social media dataset by using deep learning and topic modeling. SN Comput Sci 5:712","journal-title":"SN Comput Sci"},{"key":"21343_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-024-19171-2","volume":"84","author":"P Singh","year":"2025","unstructured":"Singh P, Tripathi MK, Patil MB, Shivendra NM (2025) Multimodal emotion recognition model via hybrid model with improved feature level fusion on facial and EEG feature set. Multimedia Tools Appl 84:1\u201336","journal-title":"Multimedia Tools Appl"},{"key":"21343_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2025.121968","volume":"704","author":"W Gong","year":"2025","unstructured":"Gong W, Wang Y, Wu Y, Gao S, Vasilakos AV, Zhang P (2025) A hybrid fusion model for group-level emotion recognition in complex scenarios. Inf Sci 704:121968","journal-title":"Inf Sci"},{"key":"21343_CR32","doi-asserted-by":"publisher","first-page":"5309","DOI":"10.1007\/s00500-016-2115-0","volume":"21","author":"VP Gon\u00e7alves","year":"2017","unstructured":"Gon\u00e7alves VP, Giancristofaro GT, Filho GP, Johnson T, Carvalho V, Pessin G, Neris VP, Ueyama J (2017) Assessing users\u2019 emotion at interaction time: a multimodal approach with multiple sensors. Soft Comput 21:5309\u20135323","journal-title":"Soft Comput"},{"key":"21343_CR33","doi-asserted-by":"publisher","first-page":"20118","DOI":"10.1007\/s11227-024-06259-7","volume":"80","author":"M Bouchene","year":"2024","unstructured":"Bouchene M (2024) Bayesian optimization of histogram of oriented gradients (hog) parameters for facial recognition. J Supercomput 80:20118\u201320149","journal-title":"J Supercomput"},{"key":"21343_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2023.100007","volume":"3","author":"AH Oliaee","year":"2023","unstructured":"Oliaee AH, Das S, Liu J, Rahman MA (2023) Using bidirectional encoder representations from transformers (Bert) to classify traffic crash severity types. Natural Language Processing Journal 3:100007","journal-title":"Natural Language Processing Journal"},{"key":"21343_CR35","doi-asserted-by":"publisher","first-page":"4791","DOI":"10.3390\/app10144791","volume":"10","author":"P Narv\u00e1ez","year":"2020","unstructured":"Narv\u00e1ez P, Gutierrez S, Percybrooks WS (2020) Automatic segmentation and classification of heart sounds using modified empirical wavelet transform and power features. Appl Sci 10:4791","journal-title":"Appl Sci"},{"key":"21343_CR36","doi-asserted-by":"crossref","unstructured":"Liu Y, Li C, Xu S, Han J (2025) Part-whole relational fusion towards multi-modal scene understanding. International Journal of Computer Vision 1\u201321.","DOI":"10.1007\/s11263-025-02393-8"},{"key":"21343_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2023.100302","volume":"14","author":"S Ghimire","year":"2023","unstructured":"Ghimire S, Nguyen-Huy T, AL-Musaylh MS, Deo RC, Casillas-P\u00e9rez D, Salcedo-Sanz S (2023) Integrated multi-head self-attention transformer model for electricity demand prediction incorporating local climate variables. Energy AI 14:100302","journal-title":"Energy AI"},{"key":"21343_CR38","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1109\/TASLP.2022.3226680","volume":"31","author":"B Xie","year":"2022","unstructured":"Xie B, Li Y, Zhao H, Pan L, Wang E (2022) A cross-attention fusion based graph convolution auto-encoder for open relation extraction. IEEE ACM Trans Audio Speech Lang Process 31:476\u2013485","journal-title":"IEEE ACM Trans Audio Speech Lang Process"},{"key":"21343_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111268","volume":"153","author":"LHM Torres","year":"2024","unstructured":"Torres LHM, Ribeiro B, Arrais JP (2024) Multi-scale cross-attention transformer via graph embeddings for few-shot molecular property prediction. Appl Soft Comput 153:111268","journal-title":"Appl Soft Comput"},{"key":"21343_CR40","doi-asserted-by":"publisher","first-page":"5235","DOI":"10.1007\/s10586-023-04221-5","volume":"27","author":"B Abdollahzadeh","year":"2024","unstructured":"Abdollahzadeh B, Khodadadi N, Barshandeh S, Trojovsk\u00fd P, Gharehchopogh FS, El-kenawy E-SM, Abualigah L, Mirjalili S (2024) Puma optimizer (PO): a novel metaheuristic optimization algorithm and its application in machine learning. Cluster Comput 27:5235\u20135283","journal-title":"Cluster Comput"},{"key":"21343_CR41","doi-asserted-by":"publisher","first-page":"6472","DOI":"10.1109\/TAI.2024.3445325","volume":"5","author":"T Meng","year":"2024","unstructured":"Meng T, Shou Y, Ai W, Yin N, Li K (2024) Deep imbalanced learning for multimodal emotion recognition in conversations. IEEE Trans Artif Intell 5:6472\u20136487","journal-title":"IEEE Trans Artif Intell"},{"key":"21343_CR42","unstructured":"Shou Y, Meng T, Ai W, Yin N, Li K (2023) Adversarial representation with intra-modal and inter-modal graph contrastive learning for multimodal emotion recognition. https:\/\/arxiv.org\/abs\/2312.16778."},{"key":"21343_CR43","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1007\/s11227-023-05513-8","volume":"80","author":"E Dalirinia","year":"2024","unstructured":"Dalirinia E, Jalali M, Yaghoobi M, Tabatabaee H (2024) Lotus effect optimization algorithm (LEA): a lotus nature-inspired algorithm for engineering design optimization. J Supercomput 80:761\u2013799","journal-title":"J Supercomput"},{"key":"21343_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122070","volume":"238","author":"A Taheri","year":"2024","unstructured":"Taheri A, RahimiZadeh K, Beheshti A, Baumbach J, Rao RV, Mirjalili S, Gandomi AH (2024) Partial reinforcement optimizer: an evolutionary optimization algorithm. Expert Syst Appl 238:122070","journal-title":"Expert Syst Appl"},{"key":"21343_CR45","volume":"33","author":"WJ AL-kubaisy","year":"2024","unstructured":"AL-kubaisy WJ, AL-Khateeb B (2024) Quokka swarm optimization: a new nature-inspired metaheuristic optimization algorithm. J Intell Syst 33:20240051","journal-title":"J Intell Syst"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21343-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21343-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21343-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T22:54:11Z","timestamp":1772060051000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21343-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,25]]},"references-count":45,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["21343"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21343-1","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,25]]},"assertion":[{"value":"27 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statement of animal and human rights"}},{"value":"The authors declare that they have no potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of potential conflict of interest"}},{"value":"All applicable institutional and\/or national guidelines for the care and use of animals were followed.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"For this type of analysis formal consent is not needed.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"The authors declare that they have no potential conflict of interest.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"201"}}