Email: suyong@tju.edu.cn

1.个人简历

宿勇，男，工学博士，讲师，硕士生导师。2019年6月毕业于天津大学，获得博士学位。目前主要从事计算机视觉、智能机器人和智慧供应链方向研究。担任IEEE Transactions on Cybernetics, ACM TOMM,ICME2019-2023, ICASSP2023等期刊和会议审稿人。热烈欢迎有理想有抱负的热血青年加入我们团队。

2.个人教学

主要讲授《深度学习》和《智能科学与技术课程设计》等课程。指导本科生发表多篇论文。其中，一人获得天津师范大学优秀本科生毕业论文（陶嘉庆，深圳大学），一人保研西安电子科技大学（杨怡），多人出国留学。

3.研究方向与成果

研究成果：近几年在《ACM TOMM》、《IEEE Transactions on Multimedia》、《Pattern Recognition》、《Computer Vision and Pattern Recognition》、《Journal of Visual Communication and Image Representation》、《Frontiers Neurorobotics》、《Signal Processing》、《IEEE International Conference on Multimedia & Expo》、《Ad Hoc Networks》、《International Conference on Acoustics, Speech and Signal Processing》、《Pattern Recognition and Computer Vision》等计算机视觉、多媒体和信号处理等相关领域重要刊物发表国际期刊会议论文30余篇，其中发表的CCF权威推荐会议期刊列表如下：

[1]Yong Su,Jianhai Zhang,Meng Xing,Weilong Peng,Zhiyong Feng;Disentangling style on dynamic aligned poses for individual identification; Ad Hoc Networks. 2021 (CCF-C)

[2]Yong Su,Simin An,Zhiyong Feng,Meng Xing,Jianhai Zhang;Spatio-Temporal Metric Learning for Individual Recognition from Locomotion; Journal of Visual Communication and Image Representation. 2020 (CCF-C)

[3]Yong Su,Zhiyong Feng,Jianhai Zhang,Weilong Peng,Meng Xing;Sequential Articulated Motion Reconstruction from a Monocular Image Sequence; ACM Transactions on Multimedia Computing, Communications and Applications 2018 (CCF-B)

[4]Yong Su,Weilong Peng,Meng Xing,Zhiyong Feng;Spatio-temporal multi-factor model for individual identification from biological motion; Ad Hoc Networks ; 2021 (CCF-C)

[5]Yong Su, Zhiyong Feng, Meng Xing. Spatio-Temporal Large Margin Nearest Neighbor (ST-LMNN) Based on Riemannian Features for Individual Identification.ICME 2018(CCF-B)

[6]Yong Su,Weilong Peng, A Convex Relaxation Approach for Learning Robust Koopman Operator. Accepted 2022 (CCF-C)

[7](通讯) Chen qi, Meng Xing, Yong Su. Energy-based Temporal Summarized Attentive Network for Zero-Shot Action Recognition . IEEE Transactions on Multimedia. 2023. (CCF-A)

[8](通讯)Meng Xing,Zhiyong Feng,Yong Su,Weilong Peng,Jianhai Zhang;Ventral & Dorsal Stream Theory based Zero-Shot Action Recognition; Pattern Recognition. 2021 (CCF-B)

[9]Yong Su,Meng Xing,Simin An,Weilong Peng;VDARN: Video Disentangling Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition; Ad Hoc Networksr. 2020 (CCF-C)

[10]Yong Su,Zhiyong Feng;Spatio-Temporal Multi-Factor Discriminant Analysis for Individual Identification; 2019 IEEE International Conference on Multimedia and Expo (ICME); 2019 (CCF-B)

[11](通讯)Meng Xing,Zhiyong Feng,Yong Su,Changjae Oh;Learning by Erasing: Conditional Entropy based Transferable Out-Of-Distribution Detection; 2022

[12](通讯).Jianhai Zhang,Zhiyong Feng,Yong Su,Meng Xing; Bayesian Covariance Representation with Global Informative Prior for 3D Action Recognition; Association for Computing Machinery; ACM Transactions on Multimedia Computing, Communications and Applications. 2021 (CCF-B)

[13]Weilong Peng,Yong Su,Keke Tang,Chao Xu,Zhiyong Feng,Mei-e Fang;Geometrical Consistency Modeling on B-Spline Parameter Domain for 3D Face Reconstruction From Limited Number of Wild Images; Frontiers in Neurorobotics. 2021

[14]Yi Yang (undergraduate) and Yong Su and Simin An. VDSSA: Ventral & Dorsal Sequential Self-attention AutoEncoder for Cognitive-Consistency Disentanglement. Pattern Recognition and Computer Vision. 2022. (CCF-C)

[15]Jianhai Zhang,Zhiyong Feng,Yong Su,Meng Xing; Discriminative Saliency-pose-attention Covariance for Action Recognition;ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2019 (CCF-B)

[16]Jianhai Zhang,Zhiyong Feng,Yong Su,Meng Xing;Cross-Covariance Matrix: Time-Shifted Correlations for 3D Action Recognition; Signal Processing .2020 (CCF-C)

[17]Meng Xing,Zhiyong Feng,Yong Su,Jianhai Zhang;An Image Cues Coding Approach for 3D Human Pose Estimation;ACM Transactions on Multimedia Computing, Communications and Applications .2019 (CCF-B)

[18]Meng Xing,Hu Jing,Zhiyong Feng,Yong Su,Weilong Peng,Zheng Jinqing;Dynamic hand gesture recognition using motion pattern and shape descriptors; Multimedia Tools and Applications; 2019 (CCF-C)

[19]Weilong Peng,Zhiyong Feng,Chao Xu,Yong Su;Parametric T-Spline Face Morphable Model for Detailed Fitting in Shape Subspace; 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017 (CCF-A)

[20]Cheng Qi,Zhiyong Feng,Meng Xing,Yong Su;DVAMN: Dual Visual Attention Matching Network for Zero-Shot Action Recognition; International Conference on Artificial Neural Networks; 2021 (CCF-C)