1. 多模态深度學習
     如圖1所示，該方向主要研究“虛拟主播”，屬于人工智能生成内容(Artificial Intelligence Generated Content, AIGC)：像人類一樣具備生成創造能力的AI技術，即生成式AI，它可以基于訓練數據和生成算法模型，自主生成創造新的文本、圖像、音樂、視頻、3D交互内容等各種形式的内容和數據，以及包括開啟科學新發現、創造新的價值和意義等。

圖1 多技能人工智能體接收、理解和播報中文新聞類視頻

圖2給出了四個具體研究内容：多模态語音分離、音視頻混合驅動的視頻生成、多模态視頻描述、三維語音合成。

（a）語音->視頻

（b）視頻->語音

圖2 虛拟主播研究内容

代表性研究成果：

[1]   Zidong Liu, Jiasong Wu, Zeyu Shen, Xin Chen, Qianyu Wu, Zhiguo Gui, Lotfi Senhadji, Huazhong Shu. Improving End-to-end Sign Language Translation with Adaptive Video Representation Enhanced Transformer.IEEE Transactions on Circuits and Systems for Video Technology, 2024, doi: 10.1109/TCSVT.2024.3376404

[2]       Jiasong Wu, Qingchun Li, Guanyu Yang, Lei Li, Lotfi Senhadji, Huazhong Shu. Self-supervised speech denoising using only noisy audio signals. Speech Communication, 2023, 149: 63-73.

[3]       Xize Wu, Jiasong Wu, Lei Zhu, Lotfi Senhadji, Huazhong Shu. Collaborative aware bidirectional semantic reasoning for video question answering. IEEE Transactions on Circuits and Systems for Video Technology, 2024. Major Revision.

[4]       Jiasong Wu, Xuan Li, Taotao Li, Fanman Meng, Youyong Kong, Guanyu Yang, Lotfi Senhadji, Huazhong Shu. CSLNSpeech: solving extended speech separation problem with the help of Chinese sign language. Speech Communication, 2024, 165, 103131.2020. 

[5]       Fanman Meng, Jiasong Wu, et al. SSWMNet: Solving The Problem Of Speech Separation While Wearing a Mask.https://github.com/fanmanqian/SSWMNetwork

2. 人工智能與信号處理的結合
   該研究方向嘗試溝通深度學習與信号處理兩個研究領域，具體包括用信号處理的方法對深度學習網絡進行解釋；将信号處理中的時頻分析方法作為模塊構建深度學習網絡（圖3）；深度學習網絡的數域擴展等。

圖3 小波變換與Vision Transformer融合

代表性研究成果：

[1]       Fuzhi Wu, Jiasong Wu, Youyong Kong, Chunfeng Yang, Guanyu Yang, Huazhong Shu, Guy Carrault, Lotfi Senhadji. Wavelet-Based Dual-Task Network. IEEE Transactions on Neural Networks and Learning Systems. 2024, minor revision.

[2]       Fuzhi Wu, Jiasong Wu, Huazhong Shu, Guy Carrault, Lotfi Senhadji. Spatial-enhanced Multi-level Wavelet Patching in Vision Transformers. IEEE Signal Processing Letters, 2024, 31: 446-450.

[3]       Fuzhi Wu, Jiasong Wu, Youyong Kong, Chunfeng Yang, Guanyu Yang, Huazhong Shu, Guy Carrault, Lotfi Senhadji. Multiscale low-frequency memory network for improved feature extraction in convolutional neural networks. The 38th AAAI Conference on Artificial Intelligence (AAAI), Vancouver, Canada, 2024, 5967-5975.

[4]       F.Z. Wu#, J.S. Wu#, Y.Y. Kong, C.F. Yang, G.Y. Yang, H.Z. Shu*, G. Carrault, L. Senhadji. Convolutional modulation theory: A bridge between convolutional neural networks and signal modulation theory. Neurocomputing, 2022, 514: 195-215.

[5]       Jiasong Wu*, Xiang Qiu, Jing Zhang, Fuzhi Wu, Youyong Kong, Guanyu Yang, Lotfi Senhadji, Huazhong Shu. Fractional wavelet based generative scattering networks. Frontiers in Neurorobotics. 2021.

[6]       J.S. Wu*, L. Xu, F.Z. Wu, Y.Y. Kong, L. Senhadji, H.Z. Shu. Deep octonion networks. Neurocomputing, vol. 397, pp. 179-191, 2020.

[7]       L. Liu, J. S. Wu, D. W. Li, L. Senhadji, H. Z. Shu*. Fractional wavelet scattering network and applications. IEEE Transactions on Biomedical Engineering, vol. 66, no. 2, pp. 553-563, 2019.

[8]       J. S. Wu*, S. J. Qiu, Y. Y. Kong, L. Y. Jiang, Y. Chen, W. K. Yang, L. Senhadji, H. Z. Shu. PCANet: An energy perspective. Neurocomputing, vol. 313, pp. 271-287, 2018.

[9]       Zeng R, Wu J S*, Shao Z H, Chen Y, Senhadji L, Shu H Z. Color image classification via quaternion principal component analysis network. Neurocomputing, vol. 216, pp. 416-428, 2016.

3. 疾病輔助診療系統開發
該方向主要研究“虛拟醫生”和“虛拟病人”，同樣屬于人工智能生成内容(AIGC)領域。

3.1 肝病輔助診療系統開發

如圖4和圖5所示開發一套多源肝病智能決策系統和肝髒疾病診療方案生成和解釋系統。

圖4 多源肝病智能決策系統

圖5 肝髒疾病診療方案生成和解釋系統

代表性研究成果：

[1]       Yingyao Ma, Jiasong Wu, et al. Multimodal Entity Linking with Dynamic Modality Selection and Interactive Prompt Learning. IEEE TKDE, 2024. (will be submitted)

[2]       Yifan Xue, Yingyao Ma, Jiasong Wu, Lotfi Senhadji, Huazhong Shu, Jian Yang. OneForKG: A Unified and Effective Framework for Various Knowledge Graph Completion. IEEE TKDE, 2024. (will be submitted )

3.2 牙颌面畸形輔助診療系統開發

如圖6所示開發一套牙颌面畸形輔助診療系統。

圖6 牙颌面畸形輔助診療系統

代表性研究成果：

[1]       Han Bao, Zhidong He, Jiasong Wu, John Baxter, Lotfi Senhadji, Hengjia Zhang, Shirin Shahrbaf, Sherif Elbarbary, Huazhong Shu, Luwei Liu, Bin Yan. Development and validation of the deep learning enhanced facial soft tissue network (FST-Net) for 3D landmarking. Progress in Orthodontics, 2024 (Submitted)

[2]       Han Bao, Zhidong He, Jiasong Wu, John Baxter, Lotfi Senhadji, Hengjia Zhang, Shirin Shahrbaf, Sherif Elbarbary, Huazhong Shu, Luwei Liu, Bin Yan. A New Automated 3D Facial Soft Tissue Landmarking Method via Deep Learning. Journal of Dental Research, 2024 (Submitted)

[3]     Zhidong He, Han Bao, Mingzhang Chen, Jiasong Wu, Luwei Liu, Lotfi Senhadji, Huazhong Shu, Bin Yan. FST-Net: Facial Soft Tissue Landmark Localization on 3dMD Scans Using Feature Fusion and Local Coordinate Regression. IEEE International Symposium on Biomedical Imaging (ISBI), 2024.

2009/07–2012/03， 雷恩第一大學，信号處理與通信， 博士(中法聯合培養)，導師：Lotfi Senhadji教授
2007/03–2012/11， bet356手机版唯一官网， 生物醫學工程， 博士， 導師：舒華忠教授
2005/09–2007/03， bet356手机版唯一官网， 生物醫學工程， 碩士研究生(提前攻博)，導師：於文雪副教授
2001/09–2005/06， 南華大學， 生物醫學工程， 學士， 導師：趙修良教授

2020/05-至今， bet356手机版唯一官网， bet356手机版唯一官网影像科學與技術系，副教授
2012/03-2020/04，bet356手机版唯一官网，bet356手机版唯一官网影像科學與技術系，講師

國家自然基金面上項目：面向中文新聞視頻場景的多模态深度學習網絡構造方法研究(2025-2028)

江蘇省重點國别國際合作項目：牙颌面畸形輔助診療系統的合作研發(2023-2026)

江蘇省産學研項目：疾病智能病案、智能篩查和智能決策系統研發(2023-2025)

中電28所項目：語音僞造和防僞識别技術研究(2022-2024)

科技創新2030新一代人工智能項目課題：基于知識圖譜和病曆的醫學證據智能體構建(2021-2024)

國家自然基金面上項目：複數及四元數域卷積神經網絡的構造方法及其應用研究(2019-2022)

[1]     Xize Wu, Jiasong Wu, Lei Zhu, Lotfi Senhadji, Huazhong Shu. Collaborative aware bidirectional semantic reasoning for video question answering. IEEE Transactions on Circuits and Systems for Video Technology, Submitted. 

[2]     Jiasong Wu, Xuan Li, Taotao Li, Fanman Meng, Youyong Kong, Guanyu Yang, Lotfi Senhadji, Huazhong Shu. CSLNSpeech: solving extended speech separation problem with the help of Chinese sign language. Speech Communication, 2024, 165, 103131.

[3]    Zidong Liu, Jiasong Wu, Zeyu Shen, Xin Chen, Qianyu Wu, Zhiguo Gui, Lotfi Senhadji, Huazhong Shu. Improving End-to-end Sign Language Translation with Adaptive Video Representation Enhanced Transformer. IEEE Transactions on Circuits and Systems for Video Technology, 2024. DOI: 10.1109/TCSVT.2024.3376404.

[4]    Fuzhi Wu, Jiasong Wu, Youyong Kong, Chunfeng Yang, Guanyu Yang, Huazhong Shu, Guy Carrault, Lotfi Senhadji. Multiscale low-frequency memory network for improved feature extraction in convolutional neural networks. AAAI, 2024 (Accepted).

[5]     Fuzhi Wu, Jiasong Wu, Huazhong Shu, Guy Carrault, Lotfi Senhadji. Spatial-enhanced Multi-level Wavelet Patching in Vision Transformers. IEEE Signal Processing Letters, 2024, 31: 446-450.2023 (Accepted).

[6]     Jiasong Wu, Qingchun Li, Guanyu Yang, Lei Li, Lotfi Senhadji, Huazhong Shu. Self-supervised speech denoising using only noisy audio signals. Speech Communication, 2023, 149: 63-73.

[7]     Zhijian Sun; Zhuhong Shao; Yuanyuan Shang; Bicao Li; Jiasong Wu; Hui Bi; Randomized nonlinear two-dimensional principal component analysis network for object recognition, Machine Vision and Applications, 2023, 34(2)：1-9.

[8]     F.Z. Wu#, J.S. Wu#, Y.Y. Kong, C.F. Yang, G.Y. Yang, H.Z. Shu*, G. Carrault, L. Senhadji. Convolutional modulation theory: A bridge between convolutional neural networks and signal modulation theory. Neurocomputing, 2022, 514: 195-215.

[9]  YT He, RJ Ge, XM Qi, Y Chen, JS Wu, JL Coatrieux,  G Y Yang,  S Li.  Learning Better Registration to Learn Better Few-Shot Medical Image Segmentation: Authenticity, Diversity, and Robustness. IEEE Transactions on Neural Networks and Learning Systems.

[10]  Jiasong Wu*, Xiang Qiu, Jing Zhang, Fuzhi Wu, Youyong Kong, Guanyu Yang, Lotfi Senhadji, Huazhong Shu. Fractional wavelet based generative scattering networks. Frontiers in Neurorobotics. 2021.

[11]  Xilin Liu, Yongfei Wu, Hao Zhang, Jiasong Wu, Liming Zhang. Quaternion discrete fractional Krawtchouk transform and its application in color image encryption and watermarking. Signal Processing. 189: 108275 (2021)

[12]  Yan Zhang, Yifei Li, Youyong Kong, Jiasong Wu, Jian Yang, Huazhong Shu, Gouenou Coatrieux. GSCFN: A graph self-construction and fusion network for semisupervised brain tissue segmentation in MRI. Neurocomputing, vol. 455, pp. 23-37, 2021.

[13]  J.S. Wu*, L. Xu, F.Z. Wu, Y.Y. Kong, L. Senhadji, H.Z. Shu. Deep octonion networks. Neurocomputing, vol. 397, pp. 179-191, 2020.

[14]  Yuting He, Guanyu Yang, Jian Yang, Yang Chen, Youyong Kong, Jiasong Wu, Lijun Tang, Xiaomei Zhu, Jean-Louis Dillenseger, Pengfei Shao, Shaobo Zhang, Huazhong Shu, Jean-Louis Coatrieux, Shuo Li. Dense biased networks with deep priori anatomy and hard region adaptation: semi-supervised learning for fine renal artery segmentation. Medical Image Analysis, vol. 63, 2020.

[15]  Li Liu, Da Chen, Laurent D. Cohen,Jiasong Wu, Michel Paques, Huazhong Shu^*, Anisotropic tubular minimal path model with fast marching front freezing scheme, Pattern Recognition (2020), 104: 107349. doi: https://doi.org/10.1016/j.patcog.2020.107349

[16]  L. Liu, J. S. Wu, D. W. Li, L. Senhadji, H. Z. Shu*. Fractional wavelet scattering network and applications. IEEE Transactions on Biomedical Engineering, vol. 66, no. 2, pp. 553-563, 2019.

授權國家發明專利30餘項。

教育部自然科學二等獎，2013

中國海洋工程咨詢協會海洋工程科學技術二等獎，2020

江蘇省教育廳高校自然科學研究類三等獎，2018

江蘇省“科技副總”，2022

bet356手机版唯一官网教學成果獎研究生教育二等獎，2021

蘇州獨墅湖科教創新區“科教骨幹人才”，2021，2023

中國國家留學基金委“國家優秀自費留學生獎學金”，2010

法國外交部“艾菲爾(Eiffel)博士獎學金”，2009

【教學】目前正在承擔《深度學習與應用》（大三上）、《人工智能算法綜合課程設計》（大四上）、《機器學習》（研一下）課程教學；曾經承擔過《運籌學》、《深度學習導論》、《計算機視覺》、《信号與系統》的本科課程教學。

【招生】歡迎對本人研究方向感興趣的同學聯系我！”興趣是最好的老師！“