学术论文

汪建洲, 巫义锐, 袁俐新, 张文逍, Jun Liu. Beyond Sample-Level Forgetting: Improving Reliability in Multimodal Unlearning. In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), 2026.

巫义锐, 刘新富, 袁俐新, 张文逍, Shivakumara Palaiahnakote. Multimedia Teaching Framework based on Cyclic Generative LLMs: Taking Sustainability Learning as an Example. Applied Soft Computing, 202, Article 115782, 2026.

袁俐新, Ningyu Du, 巫义锐, Shivakumara Palaiahnakote, Umapada Pal. Representative instance selection strategy for discriminative features. Pattern Recognition Letters, 206, 90-96, 2026.

夏宇航, 甄诚, 巫义锐, 袁俐新, 张文逍, Jun Liu. Disentangled Knowledge Forgetting in Machine Unlearning. In Proceedings of the 35th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026), 2026.

巫义锐, Qi Yan, 刘新富, Shaohua Wan, Guohua Lv, Jiehan Zhou, Joel J. P. C. Rodrigues. Edge-Cloud Collaborated Prototype Graph Network for Efficient Few-Shot Object Detection. IEEE Internet of Things Journal, 13(11), 22670-22679, 2026.

刘新富, 巫义锐, 周玉婷. Zero-shot Medical Image Classification via Large Multimodal Models and Knowledge Graphs-driven Processing. Methods, 245, 25-34, 2026.

巫义锐, 刘新富, Qi Yan, 甄诚, 袁俐新, 张文逍. LLM-centric Collaborative Computing Framework: Leveraging Industry Specified Knowledge for Open-set Visual Recognition. Applied Soft Computing, 186, Article 114028, 2026.

王紫晔, 巫义锐, Mohammed Abdel-Megeed Salem, 袁俐新, Junyang Chen, Huan Wang, Shaohua Wan. Alignment-Aware Fine-Tuning of Vision-Language Models for Out-of-Distribution Generalization. Multimedia Systems, 32(1), Article 55, 2025.

巫义锐, 刘新富, Lucia Cascone, Michele Nappi, Shaohua Wan. Plausible Deniable Medical Image Encryption by Large Language Models and Reversible Content-Aware Strategy. IEEE Journal of Biomedical and Health Informatics, 2025.

张文逍, Hossein Rahmani, Jun Liu. Unpaired 3D Shape-to-Shape Translation via Gradient-Guided Triplane Diffusion. IEEE Transactions on Visualization and Computer Graphics(CCF-A), 2025.

巫义锐, 夏宇航, Hao Li, 袁俐新, Junyang Chen, Jun Liu, Tong Lu, Shaohua Wan. Deconfound Semantic Shift and Incompleteness in Incremental Few-shot Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence(CCF-A), 2025.

巫义锐, Hao Cao, Yong Lai, Liang Zhao, Xiaoheng Deng, Shaohua Wan. Edge Computing and Few-Shot Learning Featured Intelligent Framework in Digital Twin Empowered Mobile Networks. IEEE Transactions on Network and Service Management, 2024.

秦锐, Benze Wu, 刘新富, 巫义锐. Hyperspectral Image Classification Method Based on Global Space-Spectral Attention Mechanism. Journal of Shanghai Jiaotong University (Science)(EI), 2024.

Junyang Chen, Guoxuan Zou, Pan Zhou, 巫义锐, Zhenghan Chen, Houcheng Su, Huan Wang, Zhiguo Gong. Sparse Enhanced Network: An Adversarial Generation Method for Robust Augmentation in Sequential Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence(CCF-A), 2024.

张文逍, Hossein Rahmani, Xun Yang, Jun Liu. Reverse2Complete: Unpaired Multimodal Point Cloud Completion via Guided Diffusion. Proceedings of the 32nd ACM International Conference on Multimedia(CCF-A), 2024.

张文逍, Ziqi Wang, Li Xu, Xun Yang, Jun Liu. Informative Point cloud Dataset Extraction for Classification via Gradient-based Points Moving. Proceedings of the 32nd ACM International Conference on Multimedia(CCF-A), 2024.

Guangchen Shi, Wei Zhu, 巫义锐, Danhuai Zhao, Kang Zheng, Tong Lu. Few-shot Semantic Segmentation via Perceptual Attention and Spatial Control. Proceedings of the 32nd ACM International Conference on Multimedia(CCF-A), 2024.

袁俐新, Cheng Mei, Wenhai Wang, Tong Lu. Feature Selection Based on Intrusive Outliers Rather Than All Instances. IEEE Transactions on Image Processing(CCF-A), 2024.

刘新富, 巫义锐, 周玉婷, Junyang Chen, Huan Wang, Ye Liu, Shaohua Wan. Enhancing Large Language Models with Multimodality and Knowledge Graphs for Hallucination-free Open-set Object Recognition. VLDB Workshops, 2024.

Yi Rong, Haoran Zhou, 袁俐新, Cheng Mei, Jiahao Wang, Tong Lu. CRA-PCN: Point Cloud Completion with Intra-and Inter-level Cross-Resolution Transformers. Proceedings of the AAAI Conference on Artificial Intelligence, 2024.

巫义锐, Qiran Kong, Cheng Qian, Michele Nappi, Shaohua Wan. End-PolarT: Polar Representation for End-to-End Scene Text Detection. BigDR'23(SCI), 2023.

张文逍, Huajian Zhou, Zhen Dong, Jun Liu, Qingan Yan, Chunxia Xiao. Point Cloud Completion Via Skeleton-Detail Transformer. IEEE Transactions on Visualization and Computer Graphics(CCF-A), 2023.

Hao Li, 巫义锐, Hexuan Hu, Hu Lu, Qian Huang, Shaohua Wan. Interpretable Thoracic Pathologic Prediction via Learning Group-Disentangled Representation. Methods'23(SCI), 2023.

张文逍, Huajian Zhou, Zhen Dong, Qingan Yan, Chunxia Xiao. Rank-PointRetrieval: Reranking Point Cloud Retrieval via a Visually Consistent Registration Evaluation. IEEE Transactions on Visualization and Computer Graphics(CCF-A), 2023.

巫义锐, Qiran Kong, Lai Yong, Fabio Narducci, Shaohua Wan. CDText: Scene Text Detector Based on Context-Aware Deformable Transformer. PRL'23(SCI, CCF-C), 2023.

巫义锐, Lilai Zhang, Zonghua Gu, Hu Lu, Shaohua Wan. Edge-AI-Driven Framework with Efficient Mobile Network Design for Facial Expression Recognition. ACM TECS'23(CCF-B), 2023.

巫义锐, Qiran Kong, Lilai Zhang, Aniello Castiglione, Michele Nappi, Shaohua Wan. CDT-CAD: Context-Aware Deformable Transformers for End-to-End Chest Abnormality Detection on X-Ray Images. IEEE-ACM TCBB'23(CCF-B), 2023.

Qian Cheng, 巫义锐, Aniello Castiglione, Fabio Narducci, Shaohua Wan. DA-Net: Dual Attention Network for Flood Forecasting. JSPS'23(SCI), 2023.

巫义锐, Lilai Zhang, Hao Li, Yunfei Zhang, Shaohua Wan. Feature Fusion Pyramid Network for End-to-End Scene Text Detection. ACM TALIP'23(SCI, CCF-C), 2023.

巫义锐, Benze Wu, Yunfei Zhang, Shaohua Wan. A Novel Method of Data and Feature Enhancement for Few-Shot Image Classification. Soft Computing'23(SCI, CCF-C), 2023.

巫义锐, Hao Li, Xi Feng, Andrea Casanova, Andrea F. Abate, Shaohua Wan. GDRL: An Interpretable Framework for Thoracic Pathologic Prediction. PRL'23(SCI, CCF-C), 2023.

巫义锐, Hao Cao, Guoqiang Yang, Tong Lu, Shaohua Wan. Digital Twin of Intelligent Small Surface Defect Detection with Cyber-manufacturing Systems. IEEE TOIT'22(CCF-B), 2022.

Minglei Yuan, Chunhao Cai, Tong Lu, 巫义锐, Qian Xu, Shijie Zhou. A Novel Forget-Update Module for Few-Shot Domain Generalization. PR'22(Top Journal in Pattern Recognition, CCF-B), 2022.

巫义锐, Lilai Zhang, Stefano Berretti, Shaohua Wan. Medical Image Encryption by Content-Aware DNA Computing for Secure Healthcare. IEEE TII'22(Top Journal in Industrial Informatics, 中科院一区, IF:11.648), 2022.

Guangchen Shi, 巫义锐, Jun Liu, Shaohua Wan, Wehai Wang, Tong Lu. Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation. Proceedings of the 30th ACM international conference on multimedia(CCF-A), 2022.

巫义锐, Wen Zhang, Shaohua Wan. CE-text: A Context-Aware and Embedded Text Detector in Natural Scene Images. PRL'22(SCI, CCF-C), 2022.

Yonghong Chen, Hao Li, Han Li, Wenhao Liu, 巫义锐, Qian Huang, Shaohua Wan. An Overview of Knowledge Graph Reasoning: Key Technologies and Applications. JSAN(ESCI), 2022.

巫义锐, Haifeng Guo, Chinmay Chakraborty, Mohammad R. Khosravi, Stefano Berretti, Shaohua Wan. Edge Computing Driven Low-Light Image Dynamic Enhancement for Object Detection. IEEE TNSE'22(中科院二区), 2022.

Hao Li, 巫义锐, Hexuan Hu, Hu Lu, Shaohua Wan. Learning Group-Disentangled Representation for Interpretable Thoracic Pathologic Prediction. IEEE BIBM'22(CCF-B), 2022.

袁俐新, Guoqiang Yang, Qian Xu, Tong Lu. Discriminative feature selection with directional outliers correcting for data classification. Pattern Recognition, 2022.

Qiran Kong, 巫义锐, Chi Yuan, Yongli Wang. CT-CAD: Context-Aware Transformers for End-to-End Chest Abnormality Detection on X-Rays. IEEE BIBM'21(CCF-B), 2021.

Qiran Kong, 巫义锐, Shaohua Wan. PolarText: Single-stage Scene Text Detection with Polar Representation. EUC'21(Best Paper Award,EI), 2021.

巫义锐, Pengfei Han, Zhan Zheng. Instant water body variation detection via analysis on remote sensing imagery. JRTIP'21(SCI), 2021.

Benze Wu, 巫义锐, Shaohua Wan. An Image Enhancement Method for Few-shot Classification. EUC'21(EI), 2021.

Guangchen Shi, 巫义锐. 像素聚合和特征增强的任意形状场景文本检测. 中国图象图形学报(CCF-B中文，中文核心), 2021.

Tingting Hang, Jun Feng, 巫义锐, Le Yan, Yunfeng Wang. Joint Extraction of Entities and Overlapping Relations Using Source-Target Entity Labeling. ESWA'21(SCI, CCF-C, 中科院一区), 2021.

巫义锐, Wenxiang Liu, Shaohua Wan. Multiple Attention Encoded Cascade R-CNN for Scene Text Detection. JVCIR'21(SCI, CCF-C), 2021.

巫义锐, Wenqin Mao, Jun Feng. AI for Online Customer Service: Intent Recognition and Slot Filling Based on Deep Learning Technology. MONET'21(SCI, CCF-C), 2021.

巫义锐, Hongfei Guo, Cheng Qian, Wenpeng Wang. 基于特征增强与时序感知的洪水预报模型. 人民长江(中文核心), 2021.

Jun Feng, Zhongyi Wang, 巫义锐, Yuqi Xi. Spatial and Temporal Aware Graph Convolutional Network for Flood Forecasting. IJCNN'21(CCF-C), 2021.

Guangchen Shi, 巫义锐, Shivakumara Palaiahnakote, Umapada Pal, Tong Lu. ARNet: Active-Reference Network for Few-Shot Image Semantic Segmentation. ICME'21(CCF-B), 2021.

巫义锐, Yuntao Ma, Shaohua Wan. Multi-Scale Relation Reasoning for Multi-Modal Visual Question Answering. SPIC'21(SCI, CCF-C), 2021.

Yuntao Ma, Tong Lu, 巫义锐. Multi-scale Relational Reasoning with Regional Attention for Visual Question Answering. ICPR'20(CCF-C), 2021.

Xiaofang Li, 巫义锐, Wen Zhang, Ruichao Wang, Feng Hou. Deep learning methods in real-time image super-resolution: a survey. JRTIP'20(SCI), 2020.

Pengyu Yu, 巫义锐, Shun Zhao. A Novel SMOTE Algorithm based Portrait Model for Programmers. SmartCity'20(EI), 2020.

Pengyu Yu, 巫义锐, Benze Wu. A Novel Developer Portrait Model based on Bert-Capsule Network. HPCC'20(EI), 2020.

Haifeng Guo, Tong Lu, 巫义锐. Dynamic Low-Light Image Enhancement for Object Detection via End-to-End Training. ICPR'20(CCF-C), 2020.

巫义锐, Xiaozhong Ji, Wanting Ji, Yan Tian, Helen Zhou. CASR: a context-aware residual network for single-image super-resolution. NCAA'20(SCI, CCF-C, 中科院2区), 2020.

巫义锐, Pengyu Yu. User Portrait Technology Based on Stacking Mode. CyberSciTech'20(EI), 2020.

巫义锐, Yukai Ding, Jun Feng. SMOTE-Boost-based sparse Bayesian model for flood prediction. EJWCN'20(SCI), 2020.

巫义锐, Haohang Wang, Dabao Wei, Jun Feng. 时空多特征流域场景模式库构建方法. 河海大学学报（自然版）(中文核心), 2020.

Xiaoge Song, 巫义锐, Wenhai Wang, Tong Lu. TK-Text: Multi-shaped Scene Text Detection via Instance Segmentation. MMM'20(CCF-C), 2020.

巫义锐, Dabao Wei, Jun Feng, Xiaolong Xu. Network Attacks Detection Methods Based on Deep Learning Techniques: A Survey. SCN'20(SCI, CCF-C), 2020.

张文逍, Chengjiang Long, Qingan Yan, Alix L. H. Chow, Chunxia Xiao. Multi-stage point completion network with critical set supervision. Computer Aided Geometric Design, 2020.

张文逍, Qingan Yan, Chunxia Xiao. Detail Preserved Point Cloud Completion via Separated Feature Aggregation. Proceedings of the European Conference on Computer Vision(CCF-A), 2020.

Xiaozhong Ji, 巫义锐, Tong Lu. Context-Aware Residual Network with Promotion Gates for Single Image Super-Resolution. MMM'20(CCF-C), 2019.

Yao Xiao, Minglong Xue, Tong Lu, 巫义锐, Shivakumara Palaiahnakote. A Text-Context-Aware CNN Network for Multi-oriented and Multi-language Scene Text Detection. ICDAR'19(CCF-C), 2019.

Yukai Ding, Yuelong Zhu, 巫义锐, Jun Feng, Zirun Cheng. Spatio-Temporal Attention LSTM Model for Flood Forecasting. CPSCom'19(EI), 2019.

巫义锐, Yukai Ding, Jun Feng. Sparse Bayesian Flood Forecasting Model Based on SMOTEBoost. CPSCom'19(EI), 2019.

张文逍, Chunxia Xiao. PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CCF-A), 2019.

巫义锐, Yuechao He, Palaiahnakote Shivakumara, Ziming Li, Hongxin Guo, Tong Lu. Channel-wise attention model-based fire and rating level detection in video. CIT'19(SCI), 2019.

巫义锐, Lianglei Wei, Yucong Duan. Deep spatiotemporal LSTM network with temporal pattern feature for 3D human action recognition. CI'19(SCI, CCF-C), 2019.

巫义锐, Weigang Xu, Qinghan Yu, Jun Feng, Tong Lu. Hierarchical Bayesian Network Based Incremental Model for Flood Prediction. MMM'19(CCF-C), 2019.

Yisheng Yue, Palaiahnakote Shivakumara, 巫义锐, Liping Zhu, Tong Lu, Umapada Pal. An Automatic System for Generating Artificial Fake Character Images. MMM'19(CCF-C), 2019.

巫义锐, Zhouyu Meng, Palaiahnakote Shivakumara, Tong Lu. Compressive Sensing Based Convolutional Neural Network for Object Detection. MJCS'18(SCI), 2018.

巫义锐, Yisheng Yue, Xiao Tan, Wei Wang, Tong Lu. End-To-End Chromosome Karyotyping with Data Augmentation Using GAN. ICIP'18(CCF-C), 2018.

Zhaoyang Liu, 巫义锐, Yukai Ding, Jun Feng, Tong Lu. Context and Temporal Aware Attention Model for Flood Prediction. PCM'18(CCF-C), 2018.

Sauradip Nag, Palaiahnakote Shivakumara, 巫义锐, Umapada Pal, Tong Lu. New COLD Feature Based Handwriting Analysis for Ethnicity/Nationality Identification. ICFHR'18(EI), 2018.

巫义锐, Weigang Xu, Jun Feng, Shivakumara Palaiahnakote, Tong Lu. Local and Global Bayesian Network based Model for Flood Prediction. ICPR'18(CCF-C), 2018.

巫义锐, Zhikai Li, Shivakumara Palaiahnakote, Tong Lu. Em-SLAM: a Fast and Robust Monocular SLAM Method for Embedded Systems. ICPR'18(CCF-C), 2018.

巫义锐, Zhaoyang Liu, Weigang Xu, Jun Feng, Shivakumara Palaiahnakote, Tong Lu. Context-Aware Attention LSTM Network for Flood Prediction. ICPR'18(CCF-C), 2018.

Wenhai Wang, 巫义锐, Palaiahnakote Shivakumara, Tong Lu. Cloud of Line Distribution and Random Forest Based Text Detection from Natural/Video Scene Images. MMM'18(CCF-C), 2018.

Lianglei Wei, 巫义锐, Wenhai Wang, Tong Lu. A Novel 3D Human Action Recognition Framework for Video Content Analysis. MMM'18(CCF-C), 2018.

巫义锐, Wenhai Wang, Shivakumara Palaiahnakote, Tong Lu. A Robust Symmetry-Based Method for Scene/Video Text Detection through Neural Network. 2017.

巫义锐, Zhouyu Meng, Shivakumara Palaiahnakote, Tong Lu. Compressing YOLO Network by Compressive Sensing. ACPR'17(EI), 2017.

袁俐新, ShiJin Li, YaPing Jiang. Remote Sensing Scene Classification Using a Preclassification Strategy and an Improved Structural Feature. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017.

Hengduo Li, Jun Liu, Guyue Zhang, Yuan Gao, 巫义锐. Multi-glimpse LSTM with color-depth feature fusion for human detection. ICIP'17(CCF-C), 2017.

巫义锐, Tong Lu, Zehuan Yuan, Hao Wang.. FreeScup: A Novel Platform for Assisting Sculpture Pose Design. IEEE TMM'17(CCF-B), 2017.

Yiyang Zhou, Wenhai Wang, Wenjie Guan, 巫义锐, Heng Lai, Tong Lu, Min Cai. Visual Robotic Object Grasping Through Combining RGB-D Data and 3D Meshes. MMM'17(CCF-C), 2016.

巫义锐, Palaiahnakote Shivakumara, Tong Lu, Chew Lim Tan, Michael Blumenstein, G. Hemantha Kumar. Contour Restoration of Text Components for Recognition in Video/Scene Images. IEEE TIP'16(CCF-A), 2016.

Wenhai Wang, 巫义锐, Shivakumara Palaiahnakote, Tong Lu, Jun Liu. Cloud of Line Distribution for Arbitrary Text Detection in Scene/Video/License Plate Images. PCM'17(CCF-C), 2016.

Zehuan Yuan, Tong Lu, 巫义锐. Deep-dense Conditional Random Fields for Object Co-segmentation. IJCAI'17(CCF-A), 2016.

ShiJin Li, Hui Yu, 袁俐新. A Novel Approach to Remote Sensing Image Retrieval with Multi-feature VP-Tree Indexing and Online Feature Selection. 2016 IEEE Second International Conference on Multimedia Big Data (BigMM), 2016.

巫义锐, Xianli Zhou, Tong Lu, Guo Mei, Sun Linbi. EvaToon: A novel graph matching system for evaluating cartoon drawings. ICPR'16(CCF-C), 2015.

巫义锐, Oscar Kin-Chung Au, Chiew-Lan Tai, Tong Lu. HIRM: A Handle-Independent Reduced Model for Incremental Mesh Editing. CAGD'15(SCI,CCF-B), 2015.

巫义锐, Tong Lu, Zehuan Yuan, Hao Wang.. FreeScup: A novel platform for assisting sculpture pose design. ICME'15(CCF-B,Oral), 2014.

LiMin Wang, 巫义锐, Tong Lu, Kang Chen. Multiclass object detection by combining local appearances and context. ACM MM'11(CCF-A), 2011.