[1] CanYang Guo, Ruiyao Liu, Xu Fudong, Huibin Li*, and Zengjie Song. ASDG: MLLM-based Audio Semantics for Dance Generation. In Proceedings of the 34th ACM International Conference on Multimedia (MM ’26), November 10–14, 2026, Rio de Janeiro, Brazil. ACM, New York, NY, USA, 10 pages.

[2] Yuehan Sun, Shiyun Mao, Huibin Li*, Zengjie Song. Physics-Guided Hierarchical Prompt Learning for Unified Face Attack Detection//Chinese Conference on Biometric Recognition(CCBR), 2026.

[3] Quanzhen Lu, Tingting Ren, Huibin Li*, Zengjie Song. PoincaréFace: Hyperbolic Identity Geometry Modeling for Synthetic Face Generation[C]//Chinese Conference on Biometric Recognition (CCBR), 2026.

[4] Aiyun Liu, Zengjie Song, Huibin Li*.  ePTA-Net：Emotion-guided Progressive Temporal Aggregation Network for Micro-Expression Analysis[C]//Chinese Conference on Biometric Recognition(CCBR), 2026.

[5] Yatai Sun,Zengjie Song, Huibin Li*. Enhancing Low-Quality 3D Face Recognition via Multi-Modal Fusion Based Data Generation[C]//Chinese Conference on Biometric Recognition(CCBR), 2026

[6] Chengyang Liu, Zixuan Lin, Miaolin Han, Michael K. Ng, huibin Li*.  Distilling Quasi-Conformal Mapping: A Generalizable and Efficient Solution for Wide-Angle Correction[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2026: 19686-19695.

[7] Xinyi Li, Huibin Li*. Single Image Reflection Separation via Visual State Space Model and Feature Interactions[C]//Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2025: 355-369.

[8] Xintong Han, Huibin Li*. TTT-MOT: A Test-Time Training and Adaptive Iterative Scale-Up ExpansionIoU for Multiple Object Tracking in Sports[C]//Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2025: 481-495.

[9] Miaolin Han, Huibin Li*. DocMamba. Robust Document Image Dewarping via Selective State Space Sequence Modeling[C]//International Conference on Multimedia Modeling(MMM), 2025: 304-318.

[10] Fengxun Sun, Cuican Yu, Huibin Li*. Facial Adversarial Sample Augmentation for Robust Low-quality 3D Face Recognition[C]//Chinese Conference on Biometric Recognition(CCBR), 2023: 160-169.

[11] Jingting Wang, Cuican Yu, Huibin Li*. Multi-modal Feature Guided Detailed 3D Face Reconstruction from a Single Image[C]//Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2023: 356-368.

[12] Cuican Yu, Guansong Lu, Yihan Zeng, Jian Sun, Xiaodan Liang, Huibin Li*, Zongben Xu, Songcen Xu, Weizhang, Hang Xu. Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images[C]//IEEE International Conference on Computer Vision (ICCV), 2023: 15326-15337.

[13] Shiyun Mao, Ruolin Chen, Huibin Li. Learning Optimal Transport Mapping of Joint Distribution for Cross-scenario Face Anti-spoofing[C]//Chinese Conference on Biometric Recognition(CCBR), 2022: 169-179.

[14] Jingbo Zhou, Ruiqi Zhang, Kunkun Hao, Huibin Li*, et al.Two-Stage Quality Assessment Method of Power Equipment X-Ray Image Based on Improved CenterNet[C]//2021 IEEE Far East NDT New Technology & Application Forum (FENDT). IEEE, 2021: 196-207. （优秀英文论文奖）

[15] Zihui Zhang, Cuican Yu, Shuang Xu, Huibin Li*. Learning flexibly distributional representation for low-quality 3D face recognition[C]//(AAAI), 2021: 3465-3473.

[16] Zihui Zhang, Cuican Yu, Huibin Li*, Jian Sun, Feng Liu. Learning Distribution Independent Latent Representation for 3D Face Disentanglement[C]//(3DV), IEEE, 2020: 848-857.

[17] Lingjiang Xie, Cuican Yu, Huibin Li*, Jihua Zhu. ClusterFace: Clustering-Driven Deep Face Recognition[C]//(CCBR), 2018: 377-386

[18] Asim Jan, Huaxiong Ding, Hongying Meng, Liming Chen, Huibin Li*. Accurate Facial Parts Localization and Deep Learning for 3D Facial Expression Recognition[C]// (FG), IEEE, 2018: 466-472.

[19] Ruixuan Yu, Jian Sun, Huibin Li*. Learning Spectral Transform Network on 3D Surface for Non-rigid Shape Analysis[C]//(ECCV), Workshops, 2018: 377-394.

[20] Xiaofan Wei, Huibin Li*, Jian Sun, Liming Chen. Unsupervised Domain Adaptation with Regularized Optimal Transport for Multimodal 2D+3D Facial Expression Recognition. FG 2018: 31-37.

[21] Weijian Li, Di Huang, Huibin Li*, Yunhong Wang:Automatic 4D Facial Expression Recognition Using Dynamic Geometrical Image Network. FG 2018: 24-30.

[22] Huibin Li*, Jian Sun, Liming Chen:Location-sensitive sparse representation of deep normal patterns forexpression-robust 3D face recognition. IJCB 2017: 234-242.

[23] Weijian Li, Yunhong Wang, Huibin Li*, Di Huang:Enhancing 3D Facial Expression Recognition by Exaggerating Geometry Characteristics. CCBR 2017: 191-200.

[24] Xiaofan Wei, Huibin Li*, Xianfeng David Gu:Three Dimensional Face Recognition via Surface Harmonic Mapping and Deep Learning. CCBR 2017: 66-76.

[25] Yan Yang, Jian Sun, Huibin Li*, Zongben Xu:Deep ADMM-Net for Compressive Sensing MRI. NIPS 2016: 10-18.

[26] Heran Yang, Jian Sun, Huibin Li*, Lisheng Wang, Zongben Xu:Deep Fusion Net for Multi-atlas Segmentation: Application to Cardiac MR Images. MICCAI(2) 2016: 521-528.

[27] Xiaofang Wang, Huibin Li*, C. E. Bichot, S. Masnou, L. Chen. Sparse Coding and Mid-level Super-pixel Feature for L0-Graph based Unsupervised Image Segmentation. CAIP2013: 160-168.

[28] Xiaofang Wang, Huibin Li*, C. E. Bichot, S. Masnou, L. Chen. A Graph-cut Approach to ImageSegmentation using Affinity Graph based on L0 Sparse Representation of Features. ICIP2013: 4019-4023.

[29] Wei Zeng, Huibin Li*, Jean-Marie Morvan, Liming Chen, David, Gu Xianfeng. An Automatic 3DExpression Recognition Framework based on Sparse Representation of Conformal Images. FG 2013: 1-8.

[30] Huibin Li*, Di Huang, Liming Chen, Yunhong Wang, Jean-Marie Morvan. A Group of FacialNormal Descriptors for Recognizing 3D Identical Twins. BTAS 2012: 271-277.

[31] Huibin Li*, Di Huang, Jean-Marie Morvan, Liming Chen, Yunhong Wang, 3D Facial Expression Recognition via Multiple Kernel Learning of Multi-Scale Local Normal Patterns.ICPR, 2012: 2577-2580.

[32] Remco C. Veltkamp, Stefan van Jole, Hassen Drira, Boulbaba Ben Amor, Mohamed Daoudi, Huibin Li*, Liming Chen, et al. 3D Face Model Retrieval. Euro-graphics Workshop on 3D Object Retrieval, 3DOR 2011: 89-95. (Awarded the 1st performance in terms of Rank one recognition rate).

[33] Huibin Li*, Di Huang, Jean-Marie Morvan, Liming Chen. Learning Weighted Sparse Representation of Encoded Facial Normal Information for Expression-Robust 3D Face Recognition. IJCB, 2011: 1-7.

[34] Huibin Li*, Jean-Marie Morvan, Liming Chen. 3D Facial Expression Recognition Based on Histograms of Surface Differential Quantities. ACIVS 2011: 483-494.

[35] Huibin Li*, Di Huang, Pierre Lemaire, Jean-Marie Morvan, Liming Chen. Expression Robust 3DFace Recognition via Mesh-based Histograms of Multiple Order Surface Differential Quantities.ICIP 2011: 3055-3056.

[36] Huibin Li*, Feng Liu. Image De-noising Via Sparse and Redundant Representation over LearnedDictionaries in Wavelet Domain. ICIG 2009: 754-758. 

[1] Ping He, Xiaonan Gao, Huibin Li*. MG-TVMF: Multi-grained Text-Video Matching and Fusing for Weakly Supervised Video Anomaly Detection[J]. Pattern Recognition, 2026: 113201.

[2] Shiyun Mao, Huibin Li*.Hyperbolic Metric Learning for Generalizable Face Anti-Spoofing[J].IEEE Transactions on Information Forensics & Security,2025,20:7257-7271.

[3] Ping He, Huibin Li*, Miaolin Han. A Self-Paced Multiple Instance Learning Framework for Weakly Supervised Video Anomaly Detection[J].Applied Sciences, 2025, 15(3): 1049.

[4] Qiwen Shi, Zhizhong Xi, Huibin Li*. Nighttime visible and infrared image fusion based on adversarial learning[J]. Infrared Physics & Technology, 2025, 144: 105618.

[5] Shoucheng Yan, Yang Chen, Wenfei Cao, Huibin Li*. Enhancing U-Net with low-rank attention skip block for 3D point cloud segmentation[J]. Neurocomputing, 2025, 626: 129593.

[6] Fudong Xu, Lin Wang, Huibin Li*, Zhipeng Zhu, Fan Jia. Global context volume construction and semantics-guided disparity refinement for stereo matching[J]. Neurocomputing, 2025, 617: 128995.

[7] Cuican Yu, Fengxun Sun, Zihui Zhang, Huibin Li*, Zongben Xu, Liming Chen. Adaptive representation learning and sample weighting for low-quality 3D face recognition[J]. Pattern Recognition, 2025, 159: 111161.

[8] Shiyun Mao, Ruolin Chen, Huibin Li*. Weighted joint distribution optimal transport based domain adaptation for cross-scenario face anti-spoofing[J]. International Journal of Computer Vision, 2025, 133(2): 590-610.

[9] Fudong Xu, Lin Wang, Huibin Li*. A Unified and Efficient Semi-supervised Learning Framework for Stereo Matching, Pattern Recognit, 2024,147:110128.

[10] Ping He, Fan Zhang, Huibin Li*. Adversarial and focused training of abnormal videos for weakly-supervisedanomaly detection. Pattern Recognit, 2024, 147:110119.

[11] Gang Li, Ping He, Fan Zhang, Huibin Li*. Adversarial Composite Prediction of Normal Video Dynamics for Anomaly Detection,Computer Vision and Image Understanding, 2023, 232: 103686.

[12] Cuican Yu, Zihui Zhang, Huibin Li*, Jian Sun, Zongben Xu：Meta-learning-based Adversarial Training for Deep 3D Face Recognition on Point Clouds. Pattern Recognit. 134: 109065 (2023).

[13] Henghui Zhi, Chenyang Yin, Huibin Li*, Shanmin Pang: An Unsupervised Monocular Visual Odometry Based on Multi-Scale Modeling. Sensors,2022, 22(14): 5193.

[14] Chenyang Yin, Henghui Zhi, Huibin Li*. Dense Feature Learning and Compact Cost Aggregation for Deep Stereo Matching[J].IEEE Access, 2022, 10: 100999-101010.

[15] Cuican Yu, Zihui Zhang, Huibin Li*, Jian Sun, Zongben Xu. A distribution independence based method for 3D face shape decomposition[J].CVIU, 2021, 210: 103244.

[16] Yan Yang, Jian Sun, Huibin Li*, Zongben Xu: ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing. IEEE Trans. Pattern Anal. Mach. Intell,2020, 42(3): 521-538. (入选2022年ESI高被引论文).

[17] Shiqi Liu, Jingxin Liu, Qian Zhao, Xiangyong Cao, Huibin Li*, Deyu Meng, Hongying Meng, Sheng Liu. Discovering influential factors in variational autoencoders. Pattern Recognit, 2020, 100: 107166.

[18] Ruixuan Yu, Jian Sun, Huibin Li*. Second-Order Spectral Transform Block for 3D Shape Classification and Retrieval. IEEE Trans. Image Process,2020, 29: 4530-4543.

[1] 冯珺, 汪蘭珊, 王艺丹, 韩淼林, 郭灿阳, 李欣怡, 李慧斌. 基于RAG技术的电力业务决策模型自动生成方法—大语言模型在数学建模中的应用初探[J]. 工程数学学报, 2026.（已录用）

[2] 王艺丹，冯珺，徐福冬，郭灿阳，段苏桐，郭子轩，李慧斌. 检索增强电力大模型监督微调方法[J]. 计算机与现代化, 2026.（已录用）

[3] 陈艺丹,马可,李慧斌.基于全局上下文注意力的风机叶片缺陷检测[J].计算机与数字工程,2023,51(11):2693-2699.

[4] 王静婷,李慧斌.单张图像三维人脸重建方法综述[J].计算机工程与应用,2023,59(17):1-21.（下载1091次，被引26次）

[5] 杨政,蔡迪,李慧斌.基于层次化表示的电力文本命名实体识别和匹配算法[J].计算机与现代化,2022,(5):75-81.

[6] 何平, 李刚, 李慧斌. 基于深度学习的视频异常检测方法综述[J].计算机工程与科学, 2022, 44(09):1620-1629.（下载1998次，被引62次）

[7] 职恒辉, 尹晨阳, 李慧斌. 基于深度学习的视觉里程计方法综述[J].计算机工程与应用, 2022, 58(20):1-15.（下载1329次，被引14次）

[8] 尹晨阳, 职恒辉, 李慧斌. 基于深度学习的双目立体匹配方法综述[J].计算机工程, 2022, 48(10):1-12.（下载2564次，被引71次）

[9] 黄义妨, 魏丹丹, 武淼, 李慧斌, 郭勐. 面向不同传感器与复杂场景的人脸识别系统防伪方法综述[J]. 计算机工程, 2021, 47(12): 1-18.（下载1074次，被引24次）

[10] 余璀璨, 李慧斌. 基于深度学习的人脸识别方法综述[J].工程数学学报, 2021, 38(04): 451-469.（下载9503次，被引171次）

[11] 杨政，尹春林，蔡迪，李慧斌. 一种基于成词率和谱聚类的电力文本领域词发现方法[J].电子技术应用,2021, 47(10): 29-32.

[12] 周静波,郝坤坤,刘荣海,等.基于域泛化的非均衡电力设备分/合闸X射线图像识别[J].计算机应用,2021,41(S2):286-293.