{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T08:16:37Z","timestamp":1771229797023,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Science and Technology Innovation Key R&D Program of Chongqing","award":["CSTB2024TIAD-STX0027"],"award-info":[{"award-number":["CSTB2024TIAD-STX0027"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62472059"],"award-info":[{"award-number":["62472059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Chongqing Talent Plan Project, China","award":["CSTC2024YCJH-BGZXM0022"],"award-info":[{"award-number":["CSTC2024YCJH-BGZXM0022"]}]},{"name":"the Open Research Fund of Key Labora tory of Cyberspace Big Data Intelligent Security (Chongqing University of Posts and Telecommunications), Ministry of Education","award":["CBDIS202403"],"award-info":[{"award-number":["CBDIS202403"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s10844-025-01006-7","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T03:57:54Z","timestamp":1763438274000},"page":"403-424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Frequency-aware experts with multi-stage fusion for multimodal sentiment analysis"],"prefix":"10.1007","volume":"64","author":[{"given":"Xiaofei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaochen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"issue":"11","key":"1006_CR1","doi-asserted-by":"publisher","first-page":"11418","DOI":"10.1609\/aaai.v39i11.33242","volume":"39","author":"W Ai","year":"2025","unstructured":"Ai, W., Zhang, F., Shou, Y., et al. (2025). Revisiting multimodal emotion recognition in conversation from the perspective of graph spectrum. Proceedings of the AAAI Conference on Artificial Intelligence, 39(11), 11418\u201311426. https:\/\/doi.org\/10.1609\/aaai.v39i11.33242","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"1006_CR2","doi-asserted-by":"publisher","unstructured":"Cheng, J., Zhu, X., & Yang, Z. (2025). Tf-merc: Integrating time-frequency information for multimodal emotion recognition in conversation. In: Proceedings of the 2025 International Conference on Multimedia Retrieval. Association for Computing Machinery, New York, NY, USA, ICMR \u201925, p 126\u2013134,\u00a0https:\/\/doi.org\/10.1145\/3731715.3733447","DOI":"10.1145\/3731715.3733447"},{"issue":"6","key":"1006_CR3","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/MSP.2020.3014594","volume":"37","author":"M Cheung","year":"2020","unstructured":"Cheung, M., Shi, J., Wright, O., et al. (2020). Graph signal processing and deep learning: Convolution, pooling, and topology. IEEE Signal Processing Magazine, 37(6), 139\u2013149. https:\/\/doi.org\/10.1109\/MSP.2020.3014594","journal-title":"IEEE Signal Processing Magazine"},{"key":"1006_CR4","doi-asserted-by":"publisher","unstructured":"Feng, X., Lin, Y., He, L., et\u00a0al. (2024). Knowledge-guided dynamic modality attention fusion framework for multimodal sentiment analysis. In: Al-Onaizan, Y., Bansal, M., & Chen, Y.N. (eds) Findings of the Association for Computational Linguistics: EMNLP 2024. Association for Computational Linguistics, Miami, Florida, USA, pp 14755\u201314766, https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.865","DOI":"10.18653\/v1\/2024.findings-emnlp.865"},{"key":"1006_CR5","doi-asserted-by":"publisher","unstructured":"Han, W., Chen, H., & Poria, S. (2021). Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. In: Moens, M.F., Huang, X., Specia, L., et\u00a0al. (eds) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, pp 9180\u20139192,\u00a0https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.723","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"1006_CR6","doi-asserted-by":"publisher","unstructured":"Hazarika, D., Zimmermann, R., & Poria, S. (2020). Misa: Modality-invariant and -specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM International Conference on Multimedia. Association for Computing Machinery, New York, NY, USA, MM \u201920, p 1122\u20131131, https:\/\/doi.org\/10.1145\/3394171.3413678","DOI":"10.1145\/3394171.3413678"},{"key":"1006_CR7","unstructured":"He, P., Liu, X., Gao, J., et\u00a0al. (2021). Deberta: Decoding-enhanced bert with disentangled attention. In: International Conference on Learning Representations, https:\/\/openreview.net\/forum?id=XPZIaotutsD"},{"key":"1006_CR8","doi-asserted-by":"publisher","unstructured":"Hou, M., Tang, J., Zhang, J., et al. (2019). Deep multimodal multilinear fusion with high-order polynomial pooling. Advances in Neural Information Processing Systems, 32. https:\/\/doi.org\/10.5555\/3454287.3455376","DOI":"10.5555\/3454287.3455376"},{"key":"1006_CR9","doi-asserted-by":"publisher","unstructured":"Huang, J., Tao, J., Liu, B., et\u00a0al. (2020). Multimodal transformer fusion for continuous emotion recognition. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 3507\u20133511,\u00a0https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053762","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"1006_CR10","unstructured":"Lepikhin, D., Lee, H., Xu, Y., et\u00a0al. (2021). Gshard: Scaling giant models with conditional computation and automatic sharding. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021, https:\/\/arxiv.org\/abs\/2006.16668"},{"key":"1006_CR11","doi-asserted-by":"publisher","unstructured":"Li, Y., Wang, Y., & Cui, Z. (2023). Decoupled multimodal distilling for emotion recognition. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 6631\u20136640,\u00a0https:\/\/doi.org\/10.1109\/CVPR52729.2023.00641","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"1006_CR12","doi-asserted-by":"publisher","unstructured":"Li, M., Yang, D., Zhao, X., et\u00a0al. (2024a). Correlation-decoupled knowledge distillation for multimodal sentiment analysis with incomplete modalities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 12458\u201312468,\u00a0https:\/\/doi.org\/10.1109\/CVPR52733.2024.01184","DOI":"10.1109\/CVPR52733.2024.01184"},{"key":"1006_CR13","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/s10462-023-10685-z","volume":"57","author":"Y Li","year":"2024","unstructured":"Li, Y., Ding, H., Lin, Y., et al. (2024). Multi-level textual-visual alignment and fusion network for multimodal aspect-based sentiment analysis. Artificial Intelligence Review, 57, 78. https:\/\/doi.org\/10.1007\/s10462-023-10685-z","journal-title":"Artificial Intelligence Review"},{"issue":"3","key":"1006_CR14","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1007\/s10844-025-00923-x","volume":"63","author":"Y Li","year":"2025","unstructured":"Li, Y., Liu, A., & Lu, Y. (2025). Multi-level language interaction transformer for multimodal sentiment analysis. Journal of Intelligent Information Systems, 63(3), 945\u2013964. https:\/\/doi.org\/10.1007\/s10844-025-00923-x","journal-title":"Journal of Intelligent Information Systems"},{"issue":"3","key":"1006_CR15","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1109\/TAFFC.2025.3559866","volume":"16","author":"Y Li","year":"2025","unstructured":"Li, Y., Zhu, R., & Li, W. (2025). Cormult: A semi-supervised modality correlation-aware multimodal transformer for sentiment analysis. IEEE Transactions on Affective Computing, 16(3), 2321\u20132333. https:\/\/doi.org\/10.1109\/TAFFC.2025.3559866","journal-title":"IEEE Transactions on Affective Computing"},{"key":"1006_CR16","doi-asserted-by":"publisher","unstructured":"Li, Z., Tang, F., Zhao, M., et\u00a0al. (2022). Emocaps: Emotion capsule based model for conversational emotion recognition. In: Findings of the Association for Computational Linguistics: ACL 2022,\u00a0https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.126","DOI":"10.18653\/v1\/2022.findings-acl.126"},{"key":"1006_CR17","doi-asserted-by":"publisher","unstructured":"Liu, Z., Braytee, A., Anaissi, A., et\u00a0al. (2024). Ensemble pretrained models for multimodal sentiment analysis using textual and video data fusion. In: Companion Proceedings of the ACM Web Conference 2024. Association for Computing Machinery, New York, NY, USA, WWW \u201924, p 1841\u20131848, https:\/\/doi.org\/10.1145\/3589335.3651971","DOI":"10.1145\/3589335.3651971"},{"key":"1006_CR18","doi-asserted-by":"publisher","unstructured":"Mustafa, B., Riquelme, C., Puigcerver, J., et\u00a0al. (2022). Multimodal contrastive learning with limoe: the language-image mixture of experts. In: Proceedings of the 36th International Conference on Neural Information Processing Systems, pp 9564\u20139576,\u00a0https:\/\/doi.org\/10.5555\/3600270.3600965","DOI":"10.5555\/3600270.3600965"},{"key":"1006_CR19","doi-asserted-by":"publisher","unstructured":"Ong, R.K., & Khong, A.W.H. (2025). Spectrum-based modality representation fusion graph convolutional network for multimodal recommendation. In: Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, New York, NY, USA, WSDM \u201925, p 773\u2013781,\u00a0https:\/\/doi.org\/10.1145\/3701551.3703561","DOI":"10.1145\/3701551.3703561"},{"key":"1006_CR20","doi-asserted-by":"publisher","unstructured":"Paraskevopoulos, G., Georgiou, E., & Potamianos, A. (2022). Mmlatch: Bottom-up top-down fusion for multimodal sentiment analysis. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp 4573\u20134577,\u00a0https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746418","DOI":"10.1109\/ICASSP43922.2022.9746418"},{"key":"1006_CR21","doi-asserted-by":"publisher","unstructured":"Schneider, S., Baevski, A., Collobert, R., et\u00a0al. (2019). wav2vec: Unsupervised pre-training for speech recognition. In: Interspeech, https:\/\/doi.org\/10.21437\/Interspeech.2019-1873","DOI":"10.21437\/Interspeech.2019-1873"},{"issue":"3","key":"1006_CR22","doi-asserted-by":"publisher","first-page":"1825","DOI":"10.1109\/TAFFC.2025.3541743","volume":"16","author":"P Shi","year":"2025","unstructured":"Shi, P., Hu, M., Nakagawa, S., et al. (2025). Text-guided reconstruction network for sentiment analysis with uncertain missing modalities. IEEE Transactions on Affective Computing, 16(3), 1825\u20131838. https:\/\/doi.org\/10.1109\/TAFFC.2025.3541743","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"8","key":"1006_CR23","doi-asserted-by":"publisher","first-page":"8984","DOI":"10.1609\/aaai.v38i8.28747","volume":"38","author":"Y Shin","year":"2024","unstructured":"Shin, Y., Choi, J., Wi, H., et al. (2024). An attentive inductive bias for sequential recommendation beyond the self-attention. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 8984\u20138992. https:\/\/doi.org\/10.1609\/aaai.v38i8.28747","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"1006_CR24","doi-asserted-by":"publisher","unstructured":"Sun, H., Wang, H., Liu, J., et\u00a0al. (2022). Cubemlp: An mlp-based model for multimodal sentiment analysis and depression estimation. In: Proceedings of the 30th ACM International Conference on Multimedia, pp 3722\u20133729, https:\/\/doi.org\/10.1145\/3503161.3548025","DOI":"10.1145\/3503161.3548025"},{"issue":"05","key":"1006_CR25","doi-asserted-by":"publisher","first-page":"8992","DOI":"10.1609\/aaai.v34i05.6431","volume":"34","author":"Z Sun","year":"2020","unstructured":"Sun, Z., Sarma, P., Sethares, W., et al. (2020). Learning relationships between text, audio, and video via deep canonical correlation for multimodal language analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 8992\u20138999. https:\/\/doi.org\/10.1609\/aaai.v34i05.6431","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"1006_CR26","doi-asserted-by":"publisher","unstructured":"Tao, C., Li, J., Zang, T., et\u00a0al. (2025). A multi-focus-driven multi-branch network for robust multimodal sentiment analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 1547\u20131555, https:\/\/doi.org\/10.1609\/aaai.v39i2.32146","DOI":"10.1609\/aaai.v39i2.32146"},{"key":"1006_CR27","doi-asserted-by":"publisher","first-page":"1667","DOI":"10.1007\/s10844-025-00957-1","volume":"63","author":"H Wang","year":"2025","unstructured":"Wang, H., Cao, J., Liu, J., et al. (2025). A method for multimodal sentiment analysis: adaptive interaction and multi-scale fusion. Journal of Intelligent Information Systems, 63, 1667\u20131686. https:\/\/doi.org\/10.1007\/s10844-025-00957-1","journal-title":"Journal of Intelligent Information Systems"},{"key":"1006_CR28","doi-asserted-by":"publisher","unstructured":"Wang, P., Zhou, Q., Wu, Y., et\u00a0al. (2025b). Dlf: Disentangled-language-focused multimodal sentiment analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 21180\u201321188, https:\/\/doi.org\/10.1609\/aaai.v39i20.35416","DOI":"10.1609\/aaai.v39i20.35416"},{"key":"1006_CR29","doi-asserted-by":"publisher","unstructured":"Wu, S., He, D., Wang, X., et\u00a0al. (2025). Enriching multimodal sentiment analysis through textual emotional descriptions of visual-audio content. In: Proceedings of the AAAI Conference on Artificial Intelligence, AAAI \u201925, vol\u00a039. Association for the Advancement of Artificial Intelligence, Palo Alto, CA, USA, pp 1601\u20131609,\u00a0https:\/\/doi.org\/10.1609\/aaai.v39i2.32152","DOI":"10.1609\/aaai.v39i2.32152"},{"key":"1006_CR30","doi-asserted-by":"publisher","unstructured":"Wu, Z., Zhang, Q., Miao, D., et\u00a0al. (2024). Hydiscgan: A hybrid distributed cgan for audio-visual privacy preservation in multimodal sentiment analysis. In: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence,\u00a0https:\/\/doi.org\/10.24963\/ijcai.2024\/724","DOI":"10.24963\/ijcai.2024\/724"},{"issue":"8","key":"1006_CR31","doi-asserted-by":"publisher","first-page":"7657","DOI":"10.1109\/TCSVT.2024.3376564","volume":"34","author":"Z Xie","year":"2024","unstructured":"Xie, Z., Yang, Y., Wang, J., et al. (2024). Trustworthy multimodal fusion for sentiment analysis in ordinal sentiment space. IEEE Transactions on Circuits and Systems for Video Technology, 34(8), 7657\u20137670. https:\/\/doi.org\/10.1109\/TCSVT.2024.3376564","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1006_CR32","doi-asserted-by":"publisher","unstructured":"Xu, W., Jiang, H., & Liang, X. (2024). Leveraging knowledge of modality experts for incomplete multimodal learning. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp 438\u2013446, https:\/\/doi.org\/10.1145\/3664647.3681683","DOI":"10.1145\/3664647.3681683"},{"key":"1006_CR33","doi-asserted-by":"publisher","unstructured":"Yang, D., Chen, Z., Wang, Y., et\u00a0al. (2023a). Context de-confounded emotion recognition. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 19005\u201319015, https:\/\/doi.org\/10.1109\/CVPR52729.2023.01822","DOI":"10.1109\/CVPR52729.2023.01822"},{"key":"1006_CR34","doi-asserted-by":"publisher","unstructured":"Yang, J., Yu, Y., Niu, D., et\u00a0al. (2023b). Confede: Contrastive feature decomposition for multimodal sentiment analysis. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 7617\u20137630,\u00a0https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.421","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"1006_CR35","doi-asserted-by":"publisher","unstructured":"Yang, K., Yang, D., Zhang, J., et\u00a0al. (2023c). What2comm: Towards communication-efficient collaborative perception via feature decoupling. In: Proceedings of the 31st ACM International Conference on Multimedia. Association for Computing Machinery, New York, NY, USA, MM \u201923, p 7686\u20137695,\u00a0https:\/\/doi.org\/10.1145\/3581783.3611699","DOI":"10.1145\/3581783.3611699"},{"key":"1006_CR36","doi-asserted-by":"publisher","first-page":"10790","DOI":"10.1609\/aaai.v35i12.17289","volume":"35","author":"W Yu","year":"2021","unstructured":"Yu, W., Xu, H., Yuan, Z., et al. (2021). Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 10790\u201310797. https:\/\/doi.org\/10.1609\/aaai.v35i12.17289","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"1006_CR37","doi-asserted-by":"publisher","unstructured":"Yu, W., Xu, H., Yuan, Z., et\u00a0al. (2021b). Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. In: Proceedings of the AAAI conference on Artificial Intelligence, pp 10790\u201310797,\u00a0https:\/\/doi.org\/10.1609\/aaai.v35i12.17289","DOI":"10.1609\/aaai.v35i12.17289"},{"issue":"6","key":"1006_CR38","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MIS.2016.94","volume":"31","author":"A Zadeh","year":"2016","unstructured":"Zadeh, A., Zellers, R., Pincus, E., et al. (2016). Multimodal sentiment intensity analysis in videos: Facial gestures and verbal messages. IEEE Intelligent Systems, 31(6), 82\u201388. https:\/\/doi.org\/10.1109\/MIS.2016.94","journal-title":"IEEE Intelligent Systems"},{"key":"1006_CR39","doi-asserted-by":"publisher","unstructured":"Zadeh, A., Chen, M., Poria, S., et\u00a0al. (2017a). Tensor fusion network for multimodal sentiment analysis. In: Palmer, M., Hwa, R., & Riedel, S. (eds) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Copenhagen, Denmark, pp 1103\u20131114,\u00a0https:\/\/doi.org\/10.18653\/v1\/D17-1115","DOI":"10.18653\/v1\/D17-1115"},{"key":"1006_CR40","doi-asserted-by":"publisher","unstructured":"Zadeh, A., Chen, M., Poria, S., et\u00a0al. (2017b). Tensor fusion network for multimodal sentiment analysis. In: Palmer, M., Hwa, R., & Riedel, S. (eds) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Copenhagen, Denmark, pp 1103\u20131114,\u00a0https:\/\/doi.org\/10.18653\/v1\/D17-1115","DOI":"10.18653\/v1\/D17-1115"},{"key":"1006_CR41","doi-asserted-by":"publisher","unstructured":"Zadeh, A.B., Liang, P.P., Poria, S., et\u00a0al. (2018). Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 2236\u20132246, https:\/\/doi.org\/10.18653\/v1\/P18-1208","DOI":"10.18653\/v1\/P18-1208"},{"key":"1006_CR42","doi-asserted-by":"publisher","unstructured":"Zhang, H., Wang, Y., Yin, G., et\u00a0al. (2023). Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis. In: Bouamor, H., Pino, J., & Bali, K. (eds) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Singapore, pp 756\u2013767, https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.49","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"issue":"10","key":"1006_CR43","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Zhang, Z., Li, Z., et al. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10), 1499\u20131503. https:\/\/doi.org\/10.1109\/LSP.2016.2603342","journal-title":"IEEE Signal Processing Letters"},{"key":"1006_CR44","doi-asserted-by":"publisher","unstructured":"Zhang, Q., Zhu, X., Liu, Y., et\u00a0al. (2019). Iris recognition based on adaptive optimization log-gabor filter and rbf neural network. In: Biometric Recognition. Springer International Publishing, Cham, pp 312\u2013320, https:\/\/doi.org\/10.1007\/978-3-030-31456-9_3","DOI":"10.1007\/978-3-030-31456-9_3"},{"key":"1006_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112483","volume":"304","author":"Q Zhang","year":"2024","unstructured":"Zhang, Q., Miao, D., Zhang, Q., et al. (2024). Learning adaptive shift and task decoupling for discriminative one-step person search. Knowledge-Based Systems, 304, Article 112483. https:\/\/doi.org\/10.1016\/j.knosys.2024.112483","journal-title":"Knowledge-Based Systems"},{"key":"1006_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121191","volume":"681","author":"Q Zhang","year":"2024","unstructured":"Zhang, Q., Wu, J., Miao, D., et al. (2024). Attentive multi-granularity perception network for person search. Information Sciences, 681, Article 121191. https:\/\/doi.org\/10.1016\/j.ins.2024.121191","journal-title":"Information Sciences"},{"key":"1006_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103314","volume":"124","author":"Q Zhang","year":"2025","unstructured":"Zhang, Q., Miao, D., Zhang, Q., et al. (2025). Dynamic frequency selection and spatial interaction fusion for robust person search. Information Fusion, 124, Article 103314. https:\/\/doi.org\/10.1016\/j.inffus.2025.103314","journal-title":"Information Fusion"},{"key":"1006_CR48","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Chen, M., Shen, J., et\u00a0al. (2022). Tailor versatile multi-modal learning for multi-label emotion recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 9100\u20139108, https:\/\/doi.org\/10.1609\/aaai.v36i8.20895","DOI":"10.1609\/aaai.v36i8.20895"},{"key":"1006_CR49","doi-asserted-by":"publisher","first-page":"6544","DOI":"10.1109\/TIP.2021.3093397","volume":"30","author":"Z Zhao","year":"2021","unstructured":"Zhao, Z., Liu, Q., & Wang, S. (2021). Learning deep global multi-scale and local attention features for facial expression recognition in the wild. IEEE Transactions on Image Processing, 30, 6544\u20136556. https:\/\/doi.org\/10.1109\/TIP.2021.3093397","journal-title":"IEEE Transactions on Image Processing"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-025-01006-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10844-025-01006-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-025-01006-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T07:39:42Z","timestamp":1771227582000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10844-025-01006-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["1006"],"URL":"https:\/\/doi.org\/10.1007\/s10844-025-01006-7","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"21 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 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":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}