Publications

First-author Publications

  1. Yuxing Zhi, Junhuai Li, Huaijun Wang, and Jing Chen. A Multimodal Sentiment Analysis Approach Based on Multi-view Cross-modal Fusion[J]. IEEE Transactions on Computational Social Systems, 2026, 13(1): 136-151. [link] [code]

  2. Yuxing Zhi, Shuo Liu, Jiawei Du, Huaijun Wang, Jing Chen, Dou Fan, Hailing Liu, Junhuai Li, and Jiaqi Zhou. Direction-Aware Feature Recalibration and Multi-Scale Semantic Recovery for Robust Multimodal Sentiment Analysis[C]. 2026 International Joint Conference on Neural Networks(IJCNN), 2026. (Accepted) [link]

  3. Yuxing Zhi, Junhuai Li, Huaijun Wang, Jing Chen, and Wei Wei. A Multimodal Sentiment Analysis Method Based on Fuzzy Attention Fusion[J]. IEEE Transactions on Fuzzy Systems, 2024, 32(10): 5886-5898. [link] [code]

  4. Yuxing Zhi, Junhuai Li, Huaijun Wang, Jing Chen, and Ting Cao. A Fine-Grained Tri-Modal Interaction Model for Multimodal Sentiment Analysis[C]. 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2024: 5715-5719. [link] [code]

  5. Yuxing Zhi, Jiawei Du, Yufan Guo, Junhuai Li, Huaijun Wang, Jing Chen, and Kan Wang. SHARE-GNN: Shared Spectral Hypergraph Alignment for Multimodal Emotion Recognition[J]. IEEE Transactions on Affective Computing, 2026. (In peer review) [link]

  6. Yuxing Zhi, Chuang Lin, Huaijun Wang, Junhuai Li, and Jing Chen. Boundary-aware Adaptive Bottleneck Fusion for Multimodal Sentiment Analysis[J]. Information Processing & Management, 2026. (In peer review) [link]

  7. Yuxing Zhi, Jiawei Du, Yufan Guo, Junhuai Li, Huaijun Wang, and Jing Chen. SLFAR: A Structured Latent Emotional Modeling Framework with Fragment-Aware Audio Reasoning for Tri-modal Sentiment Analysis. IEEE Transactions on Multimedia, 2026. (In peer review) [link]

Co-author Publications

  1. Jiawei Du, Yuxing Zhi, Junhuai Li, Huaijun Wang, Yufan Guo, and Fangping Xia. CFSDBN: Emotion Recognition Via Channel Feature Selection and Dynamic Brain Network[J]. IEEE Transactions on Affective Computing, 2026, 17(2): 1823-1836. [link]

  2. Jiawei Du, Yuxing Zhi, Junhuai Li, Huaijun Wang, and Yufan Guo. DGST-EMONET: A Joint Spatio-Temporal Dynamic and Topological Graph Modeling Method for EEG Emotion Recognition[C]. 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). [link]

  3. Zenghao Li, Yuxing Zhi, Weirong Dong, Huaijun Wang, Yongyang Lin, and Jiamin Li. A Low-Power Speech-Based Depression Recognition Processor With Hierarchical Local-Global Network[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2026, 34(2): 519-529. [link]

  4. Junhuai Li, Yiwei Gao, Yuxing Zhi*, Yufan Guo, Huaijun Wang, Jing Chen, and Dou Fan. Attribute-Prior Guided Diffusion Augmentation and Domain Adaptation for Human Activity Recognition[J]. Expert Systems with Applications. (In peer review, Corresponding author) [link]

  5. Xinbin Mao, Yue Li, Yuxing Zhi*, Junhuai Li, Huaijun Wang, and Rong Fei. DIB-Mamba: Decoupled Information Bottleneck Fusion Mamba for Robust Multimodal Sentiment Analysis[J]. Engineering Applications of Artificial Intelligence. (In peer review, Corresponding author) [link]

  6. Yue Li, Yuxing Zhi, Huaijun Wang, Yufan Guo, Kan Wang, Lei Yu, Rong Fei, and Junhuai Li. Cross-domain human activity recognition based on deviation-graph constrained Non-Negative Matrix Factorization[J]. Engineering Applications of Artificial Intelligence, 2025, 152: 110661. [link]

  7. Junhuai Li, Chuang Lin, Huaijun Wang, Yuxing Zhi, Jing Chen, Tao Huang. Adversarial training and cross-modal feature fusion in multimodal sentiment analysis[C]. 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). [link]

  8. Junhuai Li, Jingyi Cao, Yuxing Zhi, Huaijun Wang, Ting Cao, and Rong Fei. Cross-Domain Activity Recognition Based on Stacked Transfer Network[C]. 2024 International Joint Conference on Neural Networks (IJCNN). 2024: 1-6. [link]

  9. Minghua Zhao, Yuxing Zhi, Fei Yuan, Junhuai Li, Jing Hu, Shuangli Du, Zhenghao Shi. Deep-Block Network for AU Recognition and Expression Migration[J]. Multimedia Tools and Applications, 2023: 25733-25746. [link]