职务职称：

院长、教授、博士生导师

研究方向：

多媒体智能信息处理、计算机视觉、语音信号理解、模式识别

联系电话：

0511-88780371

电子邮箱：

mao_qr@ujs.edu.cn

博士招生专业：

计算机科学与技术（081200）

学术学位硕士招生专业：

计算机科学与技术（081200）、控制科学与工程（081100）

专业学位硕士招生专业：

电子信息计算机技术（085404）、软件工程（085405）、人工智能（085410）方向

个人简介

江苏大学计算机科学与通信工程学院教授、博士生导师。国家重点项目主持人，江苏省“333人才工程”高层次人才（第二层次），江苏省“青蓝工程”学术带头人，江苏省“六大人才高峰”高层次人才，国家“双万计划”一流专业负责人，江苏省大数据泛在感知与智能农业应用工程研究中心主任，江苏省一流课程负责人，镇江市师德先进个人。国家级项目、人才评审专家。TMM、TAC、IJCAI、CVPR等多个ACM/IEEE会刊和国际/内知名会议的审稿人和共同主席。

主要研究方向：多媒体与智能信息处理，包括复杂环境下的图像、声音以及跨媒体融合处理。在情感计算、多媒体信息处理、人机交互方面的研究成果在计算机学报、CVPR、ACMMM、TIP、TMM等国内外知名学术会议/期刊上发表论文60余篇。基于视觉语音行为监控与展现的研究成果在重症病人监护、医疗设备智能交互、驾驶员行为分析等领域进行推广应用，获得了很好的经济效益，获省部级及行业科技进步奖4项。

教研成果

奖励与荣誉：

（1）国家重点项目主持人

（2）江苏省“333人才工程”第二层次人才

（3）江苏省“青蓝工程”学术带头人

（4）江苏省“六大人才高峰”高层次人才

（5）江苏省优秀博士论文指导教师

（6）国家“双万计划”一流专业负责人

（7）江苏省大数据泛在感知与智能农业应用工程研究中心主任

（8）镇江市师德先进个人

（9）江苏省人工智能学会优秀个人会员（2017）

（10）江苏大学优秀教师、江苏大学三全育人先进个人、江苏大学优秀共产党员、江苏大学优秀学业导师等荣誉

（11）中国图象图形学学会动画与数字娱乐专委会副秘书长、江苏人人工智能学会机器学习专委会副主任、江苏省计算机学会计算机教育专委会副主任

（12）担任过ICME、ICPR、ICRR等国内外知名会议的论坛主席和workshop共同主席，是TAC、TMM、PR等知名学术期刊的审稿人。

研究领域：

本人可在计算机科学与技术专业（081200）招收博士生，在计算机科学与技术（081200）、控制科学与工程（081100）专业招收学术学位硕士研究生，在电子信息计算机技术（085404）、人工智能（085410）和软件工程（085405）招收专业学位硕士研究生，主要研究方向包括：多媒体智能信息处理、计算机视觉、图像处理、语音信号理解、模式识别等领域的科学研究和技术服务。也欢迎有兴趣的本科生加入。

主持科研项目：

1. 国家级重点项目，复杂环境下语音数据的说话人识别及关键词关联检索，主持。

2. 国家级项目，面向大规模视觉语音信号的复杂情感发现与分析方法研究，主持。

3. 国家级项目，基于情感上下文的视觉语音多模态协同情感分析方法研究，主持。

4. 国家级项目，面向复杂环境的视觉语音群体情感感知与推理，主持。

5. 江苏省重点研发计划，支持方言和情感的智能语音交互关键技术及应用，主持。

人才培养：

所指导的博士生获得江苏省优秀博士论文、并被入职高校直接聘为教授，硕士生获得江苏大学优秀硕士论文，多次在科大讯飞、Interspeech等组织的情绪识别挑战赛、声纹识别挑战赛等竞赛中获奖，硕士毕业生就职于百度、海康威视、科大讯飞等知名IT企业。

代表性论文（近三年）：

[1] Qirong Mao, Ling Zhou, Wenming Zheng, et al. Region Attention and Graph Embedding Network for Occlusion Objective Class-Based Micro-Expression Recognition[J]. IEEE Transactions on Affective Computing, 2022.

[2] Lijian Gao, Qirong Mao, Jingjing Chen, et al. Reproducibility Companion Paper: On Learning Disentangled Representation for Acoustic Event Detection[C]. Proceedings of the ACM International Conference on Multimedia. Chengdu, China, 2021, 10, 20-24: 3638-3641.

[3] Feifei Zhang, Tianzhu Zhang, Qirong Mao, et al. Geometry Guided Pose-Invariant Facial Expression Recognition[J]. IEEE Transactions on Image Processing, 2020, 29: 4445-4460.

[4] Feifei Zhang, Tianzhu Zhang, Qirong Mao, et al. A Unified Deep Model for Joint Facial Expression Recognition, Face Synthesis and Face Alignment[J]. IEEE Transactions on Image Processing, 2020, 29: 6574-6589.

[5] Feifei Zhang, Mingliang Xu, Qirong Mao, et al. Joint Attribute Manipulation and Modality Alignment Learning for Composing Text and Image to Image Retrieval[C]. Proceedings of the ACM International Conference on Multimedia. Seattle, USA, 2020, 10, 12-16: 3367-3376

[6] Feifei Zhang, Tianzhu Zhang, Qirong Mao, et al. Joint Pose and Expression Modeling for Facial Expression Recognition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, Utah, 2018, 6, 18-22: 3359-3368.

[7] Feifei Zhang, Tianzhu Zhang, Qirong Mao, et al. Facial Expression Recognition in the Wild: A Cycle-Consistent Adversarial Attention Transfer Approach[C]. Proceedings of the ACM International Conference on Multimedia. Seoul, Korea, 2018, 10, 22-26: 126-135.

[8] Ling Zhou, Qirong Mao, Xiaohua Huang, et al. Feature Refinement: An Expression-Specific Feature Learning and Fusion Method for Micro-Expression Recognition[J]. Pattern Recognition, 2022, 122: 108275.

[9] Luoyang Xue, Ang Xu, Qirong Mao, et al. Weakly Supervised Sentiment-Specific Region Discovery for VSA[J]. The Computer Journal, 2022, 65(4): 818-830.

[10] Sidheswar Routray, Qirong Mao. Phase Sensitive Masking-Based Single Channel Speech Enhancement Using Conditional Generative Adversarial Network[J]. Computer Speech and Language, 2022, 71: 101270.

[11] Qing Zhu, Qirong Mao, Hongjie Jia, et al. Convolutional Relation Network for Facial Expression Recognition in the Wild with Few-Shot Learning[J]. Expert Systems with Applications, 2022, 189: 116046.

[12] Shuangqing Qian, Lijian Gao, Hongjie Jia, Qirong Mao. Efficient Monaural Speech Separation with Multiscale Time-Delay Sampling[C]. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Marina Bay Sands Expo and Convention Center, Singapore, 2022, 5, 22-27: 6847-6851.

[13] Zi-Kai Wan, Qinghua Ren, You-cai Qin, Qirong Mao. Statistical Pyramid Dense Time Delay Neural Network for Speaker Verification[C]. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Marina Bay Sands Expo and Convention Center, Singapore, 2022, 5, 22-27: 7532-7536.

[14] Hongjie Jia, Liangjun Wang, Heping Song, Qirong Mao, et al. An Efficient Nyström Spectral Clustering Algorithm Using Incomplete Cholesky Decomposition[J]. Expert Systems with Applications, 2021, 186: 115813.

[15] Ocquaye Elias Nii Noi, Qirong Mao, et al. Cross Lingual Speech Emotion Recognition via Triple Attentive Asymmetric Convolutional Neural Network[J]. International Journal of Intelligent Systems, 2021, 36(1): 53-71.

[16] Qing Zhu, Lijian Gao, Heping Song, Qirong Mao. Learning to Disentangle Emotion Factors for Facial Expression Recognition in the Wild[J]. International Journal of Intelligent Systems, 2021, 36(6): 2511-2527.

[17] Ling Zhou, Xiuyan Shao, Qirong Mao. A Survey of Micro-Expression Recognition[J]. Image and Vision Computing, 2021, 105: 104043.

[18] Duolin Huang, Qirong Mao, Zhongchen Ma, et al. Latent Discriminative Representation Learning for Speaker Recognition[J]. Frontiers of Information Technology and Electronic Engineering, 2021, 22(5): 697-708.

[19] Duolin Huang, Qirong Mao, Zhongchen Ma, et al. Erratum to: Latent Discriminative Representation Learning for Speaker Recognition[J]. Frontiers of Information Technology and Electronic Engineering, 2021, 22(6): 914-914.

[20] Chao Qi, Jianming Zhang, Hongjie Jia, Qirong Mao, et al. Deep Face Clustering Using Residual Graph Convolutional Network[J]. Knowledge-Based Systems, 2021, 211: 106561.

[21] Luoyang Xue, Qirong Mao, Xiaohua Huang, et al. NLWSNet: A Weakly Supervised Network for Visual Sentiment Analysis in Mislabeled Web Images[J]. Frontiers of Information Technology and Electronic Engineering, 2020, 21(9): 1321-1333.

[22] Jingjing Chen, Qirong Mao, You-cai Qin, et al. Latent Source-Specific Generative Factor Learning for Monaural Speech Separation Using Weighted-Factor Autoencoder[J]. Frontiers of Information Technology and Electronic Engineering, 2020, 21(11): 1639-1650.

[23] Jingjing Chen, Qirong Mao, Dong Liu. On Synthesis for Supervised Monaural Speech Separation in Time Domain[C]. Proceedings of the International Conference on INTERSPEECH. Shanghai, China, 2020, 10, 25-29: 2627-2631.

[24] Jingjing Chen, Qirong Mao, Dong Liu. Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation[C]. Proceedings of the International Conference on INTERSPEECH. Shanghai, China, 2020, 10, 25-29: 2642-2646

[25] Mengjiao Sheng, Zhongchen Ma, Hongjie Jia, Qirong Mao, et al. Face Aging with Conditional Generative Adversarial Network Guided by Ranking-CNN C]. Proceedings of the IEEE Conference on Multimedia Information Processing and Retrieval. Online, 2020, 8, 6-8: 314-319.