Dr. and Associate Professor
School of Automation
Southeast University
Address: 2 Sipailou, Nanjing 210096, China
Email: xsy[at]seu[dot]edu[dot]cn
Siyu Xia is working as an associate professor with the School of Automation at Southeast University, Nanjing, China. He received his BE and MS degrees in automationengineering from Nanjing University of Aeronautics and Astronautics, Nanjing,China, in 2000 and 2003, respectively, and the Ph.D. degree in pattern recognition and intelligence system from Southeast University, Nanjing, China, in2006. Since then he has been working in the School of Automation at SoutheastUniversity, Nanjing, China. From 2010 to 2011, he was a visiting scholar in the Department of Computer Science and Engineering, State University of New York atBuffalo. He worked as a research scientist in the short term in the Departmentof Computer Science and Engineering, SUNY at Buffalo, in 2012. He is currentlya visiting scholar in the College of Electrical and Computer Engineering at Northeastern University, USA, from May 2018. His research interests includeimage processing, applied machine learning, social media analysis, andintelligent vision systems. He was the recipient of the Science Research Famous Achievement Award in Higher Institution of China in 2015. He has served as the reviewer of many journals including TIP, T-SMC-B, T-IFS, T-MM, IJPRAI, and Neurocomputing. He received Outstanding Reviewer Award for Journal of Neurocomputing in 2016. He has also served on the PC/SPC for the conferences including AAAI, ACM-MM, ICME, and ICMLA. He is a member of IEEE and ACM.
NEWS!
-
I will serve on the Program Committee (PC) for ACM MM 2019, AAAI 2020
-
I am co-organizing The 2nd IEEE International Workshop on Faces in Multimedia (FacesMM 2019) in conjunciton with IEEE International Conference on Multimedia and Expo (ICME) 2019
-
I am co-organizing The 9th IEEE International Workshop on Analysis and Modeling of Faces and Gestures (AMFG 2019) in conjunction with CVPR 2019
-
I am co-organizing Recognizing Families In the Wild (RFIW) COMPETITION in conjunction with IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019)
-
I am co-organizing Visual Recognition of Families In the Wild TUTORIAL in conjunction with IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019)
-
We have released the code for our paper "High-quality Ellipse Detection Based on Arc-support Line Segments"
ACADEMIC SERVICES
Organizer
The 2nd IEEE International Workshop on Faces in Multimedia (FacesMM 2019) in conjunciton with IEEE International Conference on Multimedia and Expo (ICME) 2019
Organizer
The 9th IEEE International Workshop on Analysis and Modeling of Faces and Gestures (AMFG2019) in conjunction with CVPR 2019
Organizer
Recognizing Families In the Wild (RFIW) COMPETITION in conjunction with IEEE International Conference on Automatic Face and Gesture Recognition (FG2019)
Organizer
Visual Recognition of Families In the Wild TUTORIAL in conjunction with IEEE International Conference on Automatic Face and Gesture Recognition (FG2019)
Senior PC
Reviewer
-
Changsheng, Siyu Xia, Ming Shao, and Yun Fu, Arc-support Line Segments Revisited: An Efficient and High-quality Ellipse Detection. IEEE Transactions on Image Processing (TIP), 29(1): 768-781, 2020
-
Changsheng Lu, Siyu Xia, Wanming Huang, Ming Shao, Yun Fu. Circle Detection by Arc-support Line Segments. In: The 24th IEEE International Conference on Image Processing (ICIP), 2017 (Oral Presentation)
The ellipse detector owns the features of high localization accuracy, efficiency, robustness, and stability, which comprehensively yields high-quality ellipse detection performance in front of real-world images.
Circle Detection & Ellipse Detection
-
Chengyao Zheng, Siyu Xia, Ming Shao, and Yun Fu, “Fast Facial Image Analogy with Spatial Guidance,” IEEE Conference on Automatic Face and Gesture Recognition (FG), 2019.
We propose a fast facial landmarks guided image analogy method to accelerate the reconstruction of the stylized image in deep feature domain.
Fast Facial Image Analogy
-
Chao Xia, Siyu Xia, et.al. Album to family tree: a graph based method for family relationship recognition. The 14th Asian Conference on Computer Vision (ACCV), 2018
-
Chao Xia, Siyu Xia, Yuan Zhou, Ming Shao. Graph based family relationship recognition from a single image. In: The 15th Pacific Rim International Conference on Artificial Intelligence (PRICAI), 2018
The objective is to recognize the kin relations from a family photo or album.
Album to Family Tree
-
Siyu Xia, Ming Shao and Yun Fu, “Kinship Verification through Transfer Learning,” International Joint Conferences on Artificial Intelligence (IJCAI), pp.2539-2544, 2011
-
Siyu Xia, Ming Shao, Jiebo Luo, and Yun Fu, “Understanding Kin Relationships in a Photo”, IEEE Transactions on Multimedia(T-MM), 14(4):1046-1056, 2012 (Also featured in the IEEE COMSOC MMTC R-Letter, April, 2013
-
Junkang Zhang, Siyu Xia, Hong Pan, A.K.Qin. A GENETICS-MOTIVATED UNSUPERVISED MODEL FOR TRI-SUBJECT KINSHIP VERIFICATION. In: The 23rd IEEE International Conference on Image Processing (ICIP), 2016
-
Junkang Zhang, Siyu Xia, Ming Shao, Yun Fu. Family Photo Recognition via Multiple Instance Learning. In: ACM International Conference on Multimedia Retrieval (ICMR), 2017
-
Ming Shao, Siyu Xia and Yun Fu, “Genealogical Face Recognition based on UB KinFace Database,” IEEE CVPR Workshop on Biometrics (BIOM), pp.65-70, 2011
Kinship Verification based on Facial Image
-
Junkang Zhang, Siyu Xia, Kaiyu Lu, Hong Pan, A.K.Qin. Robust Road Detection from a Single Image. In: 23st International Conference on Pattern Recognition (ICPR), 2016
-
Kaiyue Lu, Siyu Xia, Junkang Zhang, A. Kai Qin, "Robust road detection in shadow conditions," J. Electron. Imaging 25(4), 043027 (2016), doi: 10.1117/1.JEI.25.4.043027.
-
Siyu Xia, Junkang Zhang, Kaiyue Lu, A.K.Qin. Road Detection via Unsupervised Feature Learning. In: The 30th Internatinal Conference on Image and Vision Computing New Zealand (IVCNZ), 2015
-
Lu Kaiyue, Siyu Xia, Dandi Chen, Chao Xia. Unstructured Road Detection From a Single Image. In: The 10th ASIAN CONTROL CONFERENCE (ASCC), 2015