{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T03:14:30Z","timestamp":1758597270822,"version":"3.44.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T00:00:00Z","timestamp":1757030400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T00:00:00Z","timestamp":1757030400000},"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":["SIViP"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11760-025-04558-x","type":"journal-article","created":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T17:13:22Z","timestamp":1757092402000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Random-coupled neural network with binary light spectrum optimization based context-aware multimodal emotion recognition using audio, video, and text feature fusion approach"],"prefix":"10.1007","volume":"19","author":[{"given":"T. Indra","family":"Deepika","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. N.","family":"Sigappi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D. N. V. S. L. S.","family":"Indira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,5]]},"reference":[{"issue":"1","key":"4558_CR1","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1186\/s12859-023-05544-1","volume":"24","author":"A Mohammad","year":"2023","unstructured":"Mohammad, A., Siddiqui, F., Alam, M.A., Idrees, S.M.: Tri-model classifiers for EEG based mental task classification: hybrid optimization assisted framework. BMC Bioinform. 24(1), 406 (2023)","journal-title":"BMC Bioinform."},{"key":"4558_CR2","doi-asserted-by":"crossref","unstructured":"Huan, R., Zhong, G., Chen, P., Liang, R.: TriSAT: Trimodal Representation Learning for Multimodal Sentiment Analysis.\u00a0IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2024)","DOI":"10.1109\/TASLP.2024.3458812"},{"key":"4558_CR3","doi-asserted-by":"publisher","first-page":"10218","DOI":"10.1109\/ACCESS.2023.3240420","volume":"11","author":"D Pe\u00f1a","year":"2023","unstructured":"Pe\u00f1a, D., Aguilera, A., Dongo, I., Heredia, J., Cardinale, Y.: A framework to evaluate fusion methods for multimodal emotion recognition. IEEE Access 11, 10218\u201310237 (2023)","journal-title":"IEEE Access"},{"issue":"9","key":"4558_CR4","doi-asserted-by":"publisher","first-page":"6472","DOI":"10.1109\/TCSVT.2022.3163445","volume":"32","author":"GN Dong","year":"2022","unstructured":"Dong, G.N., Pun, C.M., Zhang, Z.: Temporal relation inference network for multimodal speech emotion recognition. IEEE Trans. Circuits Syst. Video Technol. 32(9), 6472\u20136485 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"4558_CR5","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.1109\/TAFFC.2021.3071503","volume":"14","author":"P Bhattacharya","year":"2021","unstructured":"Bhattacharya, P., Gupta, R.K., Yang, Y.: Exploring the contextual factors affecting multimodal emotion recognition in videos. IEEE Trans. Affect. Comput. 14(2), 1547\u20131557 (2021)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"12","key":"4558_CR6","doi-asserted-by":"publisher","first-page":"1836","DOI":"10.3390\/e24121836","volume":"24","author":"F Liu","year":"2022","unstructured":"Liu, F., Chen, J., Li, K., Tan, W., Cai, C., Ayub, M.S.: A parallel multi-modal factorized bilinear pooling fusion method based on the semi-tensor product for emotion recognition. Entropy 24(12), 1836 (2022)","journal-title":"Entropy"},{"key":"4558_CR7","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.inffus.2022.07.006","volume":"88","author":"F Zhang","year":"2022","unstructured":"Zhang, F., Li, X.C., Lim, C.P., Hua, Q., Dong, C.R., Zhai, J.H.: Deep emotional arousal network for multimodal sentiment analysis and emotion recognition. Inf. Fusion 88, 296\u2013304 (2022)","journal-title":"Inf. Fusion"},{"issue":"12","key":"4558_CR8","first-page":"13410","volume":"39","author":"J Zheng","year":"2025","unstructured":"Zheng, J., Yang, C., Zhang, T., Cao, L., Jiang, B., Fan, X., Zhu, X.: Dynamic spectral graph anomaly detection. Proc. AAAI Conf. Artif. Intell. 39(12), 13410\u201313418 (2025)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"4558_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104676","volume":"133","author":"B Mocanu","year":"2023","unstructured":"Mocanu, B., Tapu, R., Zaharia, T.: Multimodal emotion recognition using cross modal audio-video fusion with attention and deep metric learning. Image Vis. Comput. 133, 104676 (2023)","journal-title":"Image Vis. Comput."},{"key":"4558_CR10","doi-asserted-by":"publisher","first-page":"14742","DOI":"10.1109\/ACCESS.2023.3244390","volume":"11","author":"HD Le","year":"2023","unstructured":"Le, H.D., Lee, G.S., Kim, S.H., Kim, S., Yang, H.J.: Multi-label multimodal emotion recognition with transformer-based fusion and emotion-level representation learning. IEEE Access 11, 14742\u201314751 (2023)","journal-title":"IEEE Access"},{"issue":"12","key":"4558_CR11","doi-asserted-by":"publisher","first-page":"5475","DOI":"10.3390\/s23125475","volume":"23","author":"D Mamieva","year":"2023","unstructured":"Mamieva, D., Abdusalomov, A.B., Kutlimuratov, A., Muminov, B., Whangbo, T.K.: Multimodal emotion detection via attention-based fusion of extracted facial and speech features. Sensors 23(12), 5475 (2023)","journal-title":"Sensors"},{"key":"4558_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110494","volume":"144","author":"A Aslam","year":"2023","unstructured":"Aslam, A., Sargano, A.B., Habib, Z.: Attention-based multimodal sentiment analysis and emotion recognition using deep neural networks. Appl. Soft Comput. 144, 110494 (2023)","journal-title":"Appl. Soft Comput."},{"key":"4558_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108580","volume":"244","author":"AI Middya","year":"2022","unstructured":"Middya, A.I., Nag, B., Roy, S.: Deep learning based multimodal emotion recognition using model-level fusion of audio\u2013visual modalities. Knowl.-Based Syst. 244, 108580 (2022)","journal-title":"Knowl.-Based Syst."},{"issue":"4","key":"4558_CR14","doi-asserted-by":"publisher","first-page":"28","DOI":"10.3390\/mti6040028","volume":"6","author":"MC Caschera","year":"2022","unstructured":"Caschera, M.C., Grifoni, P., Ferri, F.: Emotion classification from speech and text in videos using a multimodal approach. Multimodal Technol. Interact. 6(4), 28 (2022)","journal-title":"Multimodal Technol. Interact."},{"issue":"22","key":"4558_CR15","doi-asserted-by":"publisher","first-page":"32265","DOI":"10.1007\/s11042-022-13091-9","volume":"81","author":"N Jia","year":"2022","unstructured":"Jia, N., Zheng, C., Sun, W.: A multimodal emotion recognition model integrating speech, video and MoCAP. Multimedia Tools Appl. 81(22), 32265\u201332286 (2022)","journal-title":"Multimedia Tools Appl."},{"key":"4558_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122946","volume":"245","author":"M Khan","year":"2024","unstructured":"Khan, M., Gueaieb, W., El Saddik, A., Kwon, S.: MSER: multimodal speech emotion recognition using cross-attention with deep fusion. Expert Syst. Appl. 245, 122946 (2024)","journal-title":"Expert Syst. Appl."},{"key":"4558_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103268","author":"X Zhu","year":"2025","unstructured":"Zhu, X., Wang, Y., Cambria, E., Rida, I., L\u00f3pez, J.S., Cui, L., Wang, R.: RMER-dt: robust multimodal emotion recognition in conversational contexts based on diffusion and transformers. Inf. Fusion (2025). https:\/\/doi.org\/10.1016\/j.inffus.2025.103268","journal-title":"Inf. Fusion"},{"key":"4558_CR18","doi-asserted-by":"crossref","unstructured":"Wang, R., Guo, C., Cambria, E., Rida, I., Yuan, H., Piran, M. J., de Compiegne, M. CIME: Contextual interactionbased multimodal emotion analysis with enhanced semantic information. J. Supercomput. (2025)","DOI":"10.22541\/au.173750886.60448227\/v1"},{"key":"4558_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105519","volume":"158","author":"M Gao","year":"2025","unstructured":"Gao, M., Sun, J., Li, Q., Khan, M.A., Shang, J., Zhu, X., Jeon, G.: Towards trustworthy image super-resolution via symmetrical and recursive artificial neural network. Image Vis. Comput. 158, 105519 (2025)","journal-title":"Image Vis. Comput."},{"key":"4558_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108564","volume":"260","author":"X Zhu","year":"2025","unstructured":"Zhu, X., Liu, Z., Cambria, E., Yu, X., Fan, X., Chen, H., Wang, R.: A client\u2013server based recognition system: non-contact single\/multiple emotional and behavioral state assessment methods. Comput. Methods Programs Biomed. 260, 108564 (2025)","journal-title":"Comput. Methods Programs Biomed."},{"key":"4558_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105052","volume":"85","author":"S Zhang","year":"2023","unstructured":"Zhang, S., Yang, Y., Chen, C., Liu, R., Tao, X., Guo, W., Xu, Y., Zhao, X.: Multimodal emotion recognition based on audio and text by using hybrid attention networks. Biomed. Signal Process. Control 85, 105052 (2023)","journal-title":"Biomed. Signal Process. Control"},{"issue":"1","key":"4558_CR22","doi-asserted-by":"publisher","first-page":"3605","DOI":"10.1038\/s41598-024-54077-x","volume":"14","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Wang, X., Wen, J., Zhu, X.: Wifi-based non-contact human presence detection technology. Sci. Rep. 14(1), 3605 (2024)","journal-title":"Sci. Rep."},{"issue":"3","key":"4558_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12559-025-10463-9","volume":"17","author":"R Wang","year":"2025","unstructured":"Wang, R., Wang, Y., Cambria, E., Fan, X., Yu, X., Huang, Y., Zhu, X.: Contrastive-based removal of negative information in multimodal emotion analysis. Cogn. Comput. 17(3), 1\u201316 (2025)","journal-title":"Cogn. Comput."},{"key":"4558_CR24","first-page":"18532","volume":"36","author":"YH Wu","year":"2024","unstructured":"Wu, Y.H., Wang, X., Hamaya, M.: Elastic decision transformer. Adv. Neural Inform. Process. Syst. 36, 18532 (2024)","journal-title":"Adv. Neural Inform. Process. Syst."},{"issue":"19","key":"4558_CR25","doi-asserted-by":"publisher","first-page":"8079","DOI":"10.3390\/s23198079","volume":"23","author":"MF Siddique","year":"2023","unstructured":"Siddique, M.F., Ahmad, Z., Ullah, N., Kim, J.: A hybrid deep learning approach: integrating short-time Fourier transform and continuous wavelet transform for improved pipeline leak detection. Sensors 23(19), 8079 (2023)","journal-title":"Sensors"},{"issue":"1","key":"4558_CR26","doi-asserted-by":"publisher","first-page":"516","DOI":"10.3906\/elk-1804-58","volume":"27","author":"F Makhmudkhujaev","year":"2019","unstructured":"Makhmudkhujaev, F., Iqbal, M.T.B., Ryu, B., Chae, O.: Local directional-structural pattern for person-independent facial expression recognition. Turk. J. Electr. Eng. Comput. Sci. 27(1), 516\u2013531 (2019)","journal-title":"Turk. J. Electr. Eng. Comput. Sci."},{"issue":"1","key":"4558_CR27","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TNNLS.2022.3178522","volume":"35","author":"Z Yang","year":"2022","unstructured":"Yang, Z., Ma, J., Chen, H., Zhang, J., Chang, Y.: Context-aware attentive multilevel feature fusion for named entity recognition. IEEE Trans. Neural Netw. Learn. Syst. 35(1), 973\u2013984 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"4558_CR28","doi-asserted-by":"crossref","unstructured":"Liu, H., Liu, M., Li, P., Wu, J., Jiang, X., Zuo, Z., Liu, B.: Random-coupled Neural Network.\u00a0arXiv preprint arXiv:2403.17512. (2024).","DOI":"10.3390\/electronics13214297"},{"issue":"11","key":"4558_CR29","doi-asserted-by":"publisher","first-page":"9375","DOI":"10.1109\/TNNLS.2022.3159394","volume":"34","author":"NK Tomar","year":"2022","unstructured":"Tomar, N.K., Jha, D., Riegler, M.A., Johansen, H.D., Johansen, D., Rittscher, J., Halvorsen, P., Ali, S.: Fanet: a feedback attention network for improved biomedical image segmentation. IEEE Trans. Neural Netw. Learn. Syst. 34(11), 9375\u20139388 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"4558_CR30","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1016\/j.aej.2022.12.025","volume":"67","author":"M Abdel-Basset","year":"2023","unstructured":"Abdel-Basset, M., Mohamed, R., Abouhawwash, M., Alshamrani, A.M., Mohamed, A.W., Sallam, K.: Binary light spectrum optimizer for knapsack problems: an improved model. Alexandria Eng. J. 67, 609\u2013632 (2023)","journal-title":"Alexandria Eng. J."},{"issue":"18","key":"4558_CR31","doi-asserted-by":"publisher","first-page":"53497","DOI":"10.1007\/s11042-023-17653-3","volume":"83","author":"M Tahir","year":"2024","unstructured":"Tahir, M., Halim, Z., Waqas, M., Sukhia, K.N., Tu, S.: Emotion detection using convolutional neural network and long short-term memory: a deep multimodal framework. Multimedia Tools Appl. 83(18), 53497\u201353530 (2024)","journal-title":"Multimedia Tools Appl."},{"key":"4558_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107708","volume":"130","author":"U Bilotti","year":"2024","unstructured":"Bilotti, U., Bisogni, C., De Marsico, M., Tramonte, S.: Multimodal emotion recognition via convolutional neural networks: comparison of different strategies on two multimodal datasets. Eng. Appl. Artif. Intell. 130, 107708 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"3","key":"4558_CR33","doi-asserted-by":"publisher","first-page":"1903","DOI":"10.1007\/s12652-021-03407-2","volume":"14","author":"B Pan","year":"2023","unstructured":"Pan, B., Hirota, K., Jia, Z., Zhao, L., Jin, X., Dai, Y.: Multimodal emotion recognition based on feature selection and extreme learning machine in video clips. J. Ambient. Intell. Humaniz. Comput. 14(3), 1903\u20131917 (2023)","journal-title":"J. Ambient. Intell. Humaniz. Comput."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04558-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04558-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04558-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T13:17:18Z","timestamp":1758547038000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04558-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,5]]},"references-count":33,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["4558"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04558-x","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,9,5]]},"assertion":[{"value":"27 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2025","order":4,"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":"Conflict of interest"}},{"value":"All the authors involved have agreed to participate in this submitted article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"All the authors involved in this manuscript give full consent for publication of this submitted article.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publication"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"1026"}}