{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:03:53Z","timestamp":1780934633910,"version":"3.54.1"},"reference-count":74,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Hubei Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.engappai.2026.115133","type":"journal-article","created":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T01:10:58Z","timestamp":1779585058000},"page":"115133","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P2","title":["Bidirectional mamba enhanced multimodal fusion framework for emotion recognition in conversations"],"prefix":"10.1016","volume":"179","author":[{"given":"Biao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijie","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longfei","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6443-9990","authenticated-orcid":false,"given":"Xuchu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115133_bib1","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"Iemocap: interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"Language resources and evaluation"},{"issue":"6","key":"10.1016\/j.engappai.2026.115133_bib2","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"Wavlm: large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"2","key":"10.1016\/j.engappai.2026.115133_bib3","doi-asserted-by":"crossref","first-page":"2099","DOI":"10.1007\/s10586-023-04073-z","article-title":"Emotion and sentiment analysis for intelligent customer service conversation using a multi-task ensemble framework","volume":"27","author":"Chen","year":"2024","journal-title":"Clust. Comput."},{"key":"10.1016\/j.engappai.2026.115133_bib4","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105721","article-title":"DNLN: image super-resolution with deformable non-local attention and multi-branch weighted feature fusion","volume":"162","author":"Chen","year":"2025","journal-title":"Image Vis Comput."},{"key":"10.1016\/j.engappai.2026.115133_bib5","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4652","article-title":"M2fnet: multi-modal fusion network for emotion recognition in conversation","author":"Chudasama","year":"2022"},{"key":"10.1016\/j.engappai.2026.115133_bib6","first-page":"284","article-title":"LoRa technology-an overview","author":"Devalal","year":"2018","journal-title":"2018 second international conference on electronics, communication and aerospace technology (ICECA). IEEE"},{"key":"10.1016\/j.engappai.2026.115133_bib7","author":"Ezzameli","year":"2023","journal-title":"Inf. Fusion"},{"issue":"5","key":"10.1016\/j.engappai.2026.115133_bib8","first-page":"2473","article-title":"Bafnet: bottleneck attention based fusion network for sleep apnea detection","volume":"28","author":"Fan","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.engappai.2026.115133_bib9","series-title":"CKERC: Joint Large Language Models with Commonsense Knowledge for Emotion Recognition in Conversation","author":"Fu","year":"2024"},{"key":"10.1016\/j.engappai.2026.115133_bib10","doi-asserted-by":"crossref","first-page":"154","DOI":"10.18653\/v1\/D19-1015","article-title":"Dialoguegcn: a graph convolutional neu ral network for emotion recognition in conversation","author":"Ghosal","year":"2019","journal-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th In ternational Joint Conference on Natural Language Processing (EMNLP-IJCNLP)"},{"key":"10.1016\/j.engappai.2026.115133_bib11","author":"Gu","year":"2023","journal-title":"Mamba: Linear-time sequence modeling with selective state spaces"},{"key":"10.1016\/j.engappai.2026.115133_bib12","first-page":"2122","article-title":"Conversational memory network for emotion recognition in dyadic dialogue videos","author":"Hazarika","year":"2018","journal-title":"Proceedings of the Conference. Association for Computational Linguistics. North American Chapter. Meeting: volume 2018. NIH Public Access"},{"key":"10.1016\/j.engappai.2026.115133_bib13","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1145\/3394171.3413678","article-title":"Misa: modality-invariant and-specific representations for multi-modal sentiment analysis","author":"Hazarika","year":"2020","journal-title":"Proceedings of the 28th ACM international conference on multimedia"},{"key":"10.1016\/j.engappai.2026.115133_bib14","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition[C]","author":"He","year":"2016"},{"key":"10.1016\/j.engappai.2026.115133_bib15","author":"Hu","year":"2021","journal-title":"Dialogue: Contextual reasoning networks for emotion recognition in conversations"},{"key":"10.1016\/j.engappai.2026.115133_bib16","author":"Hu","year":"2022","journal-title":"Unimse: Towards unified multi-modal sentiment analysis and emotion recognition"},{"key":"10.1016\/j.engappai.2026.115133_bib17","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2025.122704","article-title":"3WD-DRT: a three-way decision enhanced dynamic routing transformer for cost-sensitive multimodal sentiment analysis","volume":"725","author":"Jiang","year":"2026","journal-title":"Inf. Sci."},{"key":"10.1016\/j.engappai.2026.115133_bib18","author":"Kim","year":"2021","journal-title":"Emoberta: Speaker-aware emotion recognition in conversation with roberta"},{"issue":"8","key":"10.1016\/j.engappai.2026.115133_bib19","doi-asserted-by":"crossref","first-page":"14037","DOI":"10.1109\/TNNLS.2024.3512505","article-title":"Novel discretized zeroing neural network models for time-varying optimization aided with predictor-corrector methods","volume":"36","author":"Kong","year":"2025","journal-title":"IEEE Transact. Neural Networks Learn. Syst."},{"key":"10.1016\/j.engappai.2026.115133_bib20","series-title":"Instructerc: Reforming Emotion Recognition in Conversation with multi-task retrieval-augmented Large Language Models","author":"Lei","year":"2023"},{"issue":"10","key":"10.1016\/j.engappai.2026.115133_bib21","first-page":"11002","article-title":"Contrast and generation make bart a good dialogue emotion recognizer","volume":"36","author":"Li","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115133_bib22","author":"Li","year":"2022","journal-title":"EmoCaps: Emotion capsule based model for conversational emotion recognition"},{"key":"10.1016\/j.engappai.2026.115133_bib23","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126427","article-title":"GraphMFT: a graph network based multi-modal fusion technique for emotion recognition in conversation","volume":"550","author":"Li","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.engappai.2026.115133_bib24","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1109\/TMM.2023.3260635","article-title":"GraphCFC: a directed graph based cross-modal feature complementation approach for multi-modal conversational emotion recognition","volume":"26","author":"Li","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.115133_bib25","author":"Li","year":"2024","journal-title":"Mamba-Enhanced Text-Audio-Video Alignment Network for Emotion Recognition in Conversations"},{"key":"10.1016\/j.engappai.2026.115133_bib26","author":"Li","year":"2025","journal-title":"GatedxLSTM: A multi-modal Affective Computing Approach for Emotion Recognition in Conversations"},{"key":"10.1016\/j.engappai.2026.115133_bib27","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1145\/3731715.3733388","article-title":"MIMCL: multi-layer interaction module with contrastive learning for speech emotion recognition","author":"Li","year":"2025","journal-title":"Proceedings of the 2025 International Conference on Multimedia Retrieval"},{"key":"10.1016\/j.engappai.2026.115133_bib28","author":"Liu","year":"2018","journal-title":"Efficient low-rank multi-modal fusion with modality-specific factors"},{"key":"10.1016\/j.engappai.2026.115133_bib29","author":"Liu","year":"2019","journal-title":"Roberta: A robustly optimized bert pretraining approach"},{"key":"10.1016\/j.engappai.2026.115133_bib30","article-title":"Emotion detection for misinformation: a review","author":"Liu","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.115133_bib31","first-page":"1","article-title":"UniFES: a unified recurrent network for quality enhancement and stabilization in face videos","author":"Liu","year":"2026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.115133_bib32","article-title":"A hyper-graph based contextual relationship modeling method for multi-modal emotion recognition in conversation","author":"Lu","year":"2024","journal-title":"IEEE Trans. Multimed."},{"issue":"5","key":"10.1016\/j.engappai.2026.115133_bib33","doi-asserted-by":"crossref","first-page":"4576","DOI":"10.1109\/TCSVT.2024.3515652","article-title":"StegMamba: distortion-free immune-cover for multi-image steganography with state space model","volume":"35","author":"Luo","year":"2025","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"10.1016\/j.engappai.2026.115133_bib34","doi-asserted-by":"crossref","first-page":"2685","DOI":"10.1007\/s00521-020-05063-7","article-title":"HAN-ReGRU: hierarchical attention network with residual gated recurrent unit for emotion recognition in conversation","volume":"33","author":"Ma","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.engappai.2026.115133_bib35","first-page":"6818","article-title":"Dialoguernn: anattentivernnforemotion detection in conversations","volume":"33","author":"MajumderN","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115133_bib36","doi-asserted-by":"crossref","DOI":"10.1109\/TAI.2024.3445325","article-title":"Deep imbalanced learning for multi-modal emotion recognition in conversations","author":"Meng","year":"2024","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"10.1016\/j.engappai.2026.115133_bib38","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127109","article-title":"A multi-message passing framework based on heterogeneous graphs in conversational emotion recognition","volume":"569","author":"Meng","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.engappai.2026.115133_bib39","doi-asserted-by":"crossref","first-page":"873","DOI":"10.18653\/v1\/P17-1081","article-title":"Context-dependent sentiment analysis in user-generated videos","author":"Poria","year":"2017","journal-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"},{"key":"10.1016\/j.engappai.2026.115133_bib40","doi-asserted-by":"crossref","first-page":"527","DOI":"10.18653\/v1\/P19-1050","article-title":"Meld: a multi-modal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2019","journal-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics"},{"issue":"3","key":"10.1016\/j.engappai.2026.115133_bib41","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1109\/TAFFC.2023.3273589","article-title":"Multi-party conversation modeling for emotion recognition","volume":"15","author":"Quan","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.engappai.2026.115133_bib42","first-page":"2359","article-title":"Integrating multi-modal information in large pre-trained transformers","volume":"2020","author":"Rahman","year":"2020","journal-title":"Proceedings of the conference. Association for computational linguistics. Meeting"},{"key":"10.1016\/j.engappai.2026.115133_bib43","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"10.1016\/j.engappai.2026.115133_bib44","author":"Schiff","year":"2024","journal-title":"Caduceus: Bi-directional equivariant long-range dna sequence modeling"},{"key":"10.1016\/j.engappai.2026.115133_bib45","first-page":"1","article-title":"Color retinal image enhancement using CLAHE","author":"Setiawan","year":"2013","journal-title":"International conference on ICT for smart society. IEEE"},{"key":"10.1016\/j.engappai.2026.115133_bib46","author":"Shen","year":"2021","journal-title":"Directed acyclic graph network for conversational emotion recognition"},{"issue":"Long Papers","key":"10.1016\/j.engappai.2026.115133_bib47","doi-asserted-by":"crossref","first-page":"14752","DOI":"10.18653\/v1\/2023.acl-long.824","article-title":"MultiEMO: an attention-based correlation-aware multi-modal fusion framework for emotion recognition in conversations","volume":"1","author":"Shi","year":"2023","journal-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics"},{"key":"10.1016\/j.engappai.2026.115133_bib48","first-page":"6558","article-title":"multi-modal transformer for unaligned multi-modal language sequences","volume":"2019","author":"Tsai","year":"2019","journal-title":"Proceedings of the conference. Association for computational linguistics. Meeting"},{"key":"10.1016\/j.engappai.2026.115133_bib49","first-page":"1","article-title":"Context-and sentiment-aware networks for emotion recognition in conversation","volume":"1","author":"Tu","year":"2022","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"10.1016\/j.engappai.2026.115133_bib50","first-page":"30","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115133_bib51","first-page":"5281","article-title":"An efficient approach to informative feature extraction from multi-modal data","volume":"33","author":"Wang","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"6","key":"10.1016\/j.engappai.2026.115133_bib52","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-021-0236-9","article-title":"ResLNet: deep residual LSTM network with longer input for action recognition","volume":"16","author":"Wang","year":"2022","journal-title":"Front. Comput. Sci."},{"issue":"4","key":"10.1016\/j.engappai.2026.115133_bib53","doi-asserted-by":"crossref","DOI":"10.1002\/aisy.202200131","article-title":"TASTA: text-assisted spatial and temporal attention network for video question answering","volume":"5","author":"Wang","year":"2023","journal-title":"Adv. Intell. Syst."},{"issue":"4","key":"10.1016\/j.engappai.2026.115133_bib54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13735-024-00347-3","article-title":"Multi-modal emotion recognition using tensor decomposition fusion and self-supervised multi-tasking","volume":"13","author":"Wang","year":"2024","journal-title":"International Journal of Multimedia Information Retrieval"},{"key":"10.1016\/j.engappai.2026.115133_bib55","doi-asserted-by":"crossref","DOI":"10.1016\/j.array.2025.100445","article-title":"RAFT: robust adversarial fusion transformer for multi-modal sentiment analysis","volume":"27","author":"Wang","year":"2025","journal-title":"Array"},{"key":"10.1016\/j.engappai.2026.115133_bib56","doi-asserted-by":"crossref","DOI":"10.1007\/s12559-025-10463-9","article-title":"Contrastive-based removal of negative information in multi-modal emotion analysis","volume":"17","author":"Wang","year":"2025","journal-title":"Cogn. Comput."},{"key":"10.1016\/j.engappai.2026.115133_bib57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TCSS.2025.3613939","article-title":"CIME: contextual interaction-based multi-modal emotion analysis with enhanced semantic information","author":"Wang","year":"2025","journal-title":"IEEE Trans. Comput. Social Syst."},{"key":"10.1016\/j.engappai.2026.115133_bib58","first-page":"1","article-title":"Knowledge generation and distillation for road segmentation in intelligent transportation systems","author":"Wang","year":"2025","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"10.1016\/j.engappai.2026.115133_bib59","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1145\/3343031.3351034","article-title":"MMGCN: multi-modal graph convolution network for personalized recommendation of micro-video","author":"Wei","year":"2019","journal-title":"Proceedings of the 27th ACM international conference on multimedia"},{"key":"10.1016\/j.engappai.2026.115133_bib60","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103809","article-title":"Integrating audio-visual text generation with contrastive learning for enhanced multi-modal emotion analysis","volume":"127","author":"Xiang","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.115133_bib61","first-page":"4055","article-title":"A dual contrastive learning framework for enhanced multi-modal conversational emotion recognition","author":"Xie","year":"2025","journal-title":"Proceedings of the 31st International Conference on Computational Linguistics"},{"issue":"2","key":"10.1016\/j.engappai.2026.115133_bib62","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1109\/TAFFC.2023.3280038","article-title":"Disentangled variational autoencoder for emotion recognition in conversations","volume":"15","author":"Yang","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.engappai.2026.115133_bib63","article-title":"Cvan: a novel sleep staging method via cross-view alignment network","author":"Yang","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"5","key":"10.1016\/j.engappai.2026.115133_bib64","doi-asserted-by":"crossref","first-page":"4260","DOI":"10.1007\/s10489-024-05355-8","article-title":"Cross-modal contrastive learning for multi-modal sentiment recognition","volume":"54","author":"Yang","year":"2024","journal-title":"Appl. Intell."},{"issue":"12","key":"10.1016\/j.engappai.2026.115133_bib65","first-page":"10790","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multi-modal sentiment analysis[C]","volume":"35","author":"Yu","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115133_bib66","author":"Zadeh","year":"2017","journal-title":"Tensor fusion network for multi-modal sentiment analysis"},{"key":"10.1016\/j.engappai.2026.115133_bib67","first-page":"4429","article-title":"Knowledge aware emotion recognition in textual conversations via multi-task incremental transformer","author":"Zhang","year":"2020","journal-title":"Proceedings of the 28th International Conference on Computational Linguistics"},{"issue":"5","key":"10.1016\/j.engappai.2026.115133_bib68","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/MIS.2025.3597120","article-title":"A generative random modality dropout framework for robust multi-modal emotion recognition","volume":"40","author":"Zhang","year":"2025","journal-title":"IEEE Intell. Syst."},{"key":"10.1016\/j.engappai.2026.115133_bib69","first-page":"4524","article-title":"CauAIN: causal aware interaction network for emotion recognition in conversations","author":"Zhao","year":"2022","journal-title":"IJCAI"},{"issue":"18","key":"10.1016\/j.engappai.2026.115133_bib70","doi-asserted-by":"crossref","first-page":"56039","DOI":"10.1007\/s11042-023-17347-w","article-title":"Emotion recognition based on brain-like multi-modal hierarchical perception","volume":"83","author":"Zhu","year":"2024","journal-title":"Multimed. Tool. Appl."},{"issue":"18","key":"10.1016\/j.engappai.2026.115133_bib71","doi-asserted-by":"crossref","first-page":"56039","DOI":"10.1007\/s11042-023-17347-w","article-title":"Emotion recognition based on brain-like multi-modal hierarchical perception","volume":"83","author":"Zhu","year":"2024","journal-title":"Multimed. Tool. Appl."},{"key":"10.1016\/j.engappai.2026.115133_bib72","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.1007\/s12559-024-10287-z","article-title":"A review of key technologies for emotion analysis using multi-modal information","volume":"16","author":"Zhu","year":"2024","journal-title":"Cogn. Comput."},{"key":"10.1016\/j.engappai.2026.115133_bib73","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103268","article-title":"RMER-DT: robust multi-modal emotion recognition in conversational contexts based on diffusion and transformers","volume":"123","author":"Zhu","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.115133_bib74","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2024.108564","article-title":"A client-server based recognition system: non-contact single\/multiple emotional and behavioral state assessment methods","volume":"260","author":"Zhu","year":"2025","journal-title":"Comput. Methods Progr. Biomed."},{"issue":"8","key":"10.1016\/j.engappai.2026.115133_bib75","doi-asserted-by":"crossref","DOI":"10.1007\/s40747-025-01931-8","article-title":"EMVAS: end-to-end multi-modal emotion visualization analysis system","volume":"11","author":"Zhu","year":"2025","journal-title":"Complex Intell. Syst."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626014168?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626014168?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:50:40Z","timestamp":1780933840000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626014168"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":74,"alternative-id":["S0952197626014168"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115133","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Bidirectional mamba enhanced multimodal fusion framework for emotion recognition in conversations","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115133","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115133"}}