Home

The Agency for Science, Technology and Research (A*STAR)

1 Fusionopolis Way, #16-16 Connexis, 138632, Singapore

Email: xuxinx@ihpc.a-star.edu.sg, xxxing1987@gmail.com

Bio:

Xinxing Xu is a scientist with Institute of High Performance Computing (IHPC), Astar, Singapore. He obtained the bachelor's degree in Electronic Engineering and Information Science (EEIS) in University of Science and Technology of China (USTC) in 2009, and also his PhD degree from the Nanyang Technological University (NTU). His supervisor was Professor Dong Xu, and he also works closely with Processor Ivor Wai-Hung Tsang.

Call for papers: 1st MICCAI Workshop on "Resource-Efficient Medical Image Analysis" (REMIA), 2022. [Link]

News:

Job Opennings on AI for Heathcare, CV, NLP, ML, MIA; Please send me your CV today (xuxinx@ihpc.a-star.edu.sg)

2021-6: 2 papers accepted by MICCAI 2021!

2021-6: STEMTogether Interview by Science Centre Singapore [STEMIncSCS FB page] [YouTube short version] [YouTube].

2021-4: 1 paper accepted by IJCAI 2021!

2014-5: LibMKL: easy to use matlab code for the soft margin MKLs (including SM1MKL and LpMKL) released!

Research Interests:

  • Machine Learning: Multiple Kernel Learning (MKL), Learning using Privileged Information, Distance Metric Learning

    • Deep Learning, Convolution Neural Networks (CNN), Long Short-term Memory (LSTM), Deep Reinforcement Learning, Transformer

  • Computer Vision: Object Classification, Scene Classification, Video Event Recognition, Video Concept Detection, Action Recognition, Face Verification, Human Gait Recognition, Person Re-identification.

    • Digital Healthcare: Eye diseases detection from Fundus/OCT images, lung disease detection from X-ray images, heart disease detection from electrical medical records.

    • Text Categorization: Text Classification, Web Page classification.

    • Recommender System: Click sequence prediction.

Thesis: Learning with Multiple Representations: Algorithms and Applications

Selected Publications:

    • Shaohua Li, Xiuchao Sui, Jie Fu, Huazhu Fu, Xiangde Luo, Yangqin Feng, Xinxing Xu, Yong Liu, Daniel Ting, Rick Siow Mong Goh. Few-Shot Domain Adaptation with Polymorphic Transformers. MICCAI 2021. Accepted.

    • Yanyu Xu, Xinxing Xu, Lei Jin, Shenghua Gao, Rick Siow Mong Goh, Daniel Ting, Yong Liu. Partially-Supervised Learning for Vessel Segmentation in Ocular Images. MICCAI 2021. Accepted.

    • Shaohua Li, Xiuchao Sui, Xiangde Luo, Xinxing Xu, Yong Liu, Rick Siow Mong Goh. Medical Image Segmentation Using Squeeze-and-Expansion Transformers. Accepted by the 30th International Joint Conference on Artificial Intelligence (IJCAI'2021). [PDF]

    • Tien-En Tan, FRCOphth, Ayesha Anees, MSc, Cheng Chen, MSc, Shaohua Li, PhD, Xinxing Xu, PhD, Zengxiang Li, PhD, Zhe Xiao, PhD, Yechao Yang, BSc, Xiaofeng Lei, MSc, Marcus Ang, FRCS (Ed), Audrey Chia, FRANZCO, Shu Yen Lee, FRCS (Ed), Edmund Yick Mun Wong, FRCS (Ed), Prof Ian Yew San Yeo, FRCS (Ed), Yee Ling Wong, PhD, Quan V Hoang, MD, Ya Xing Wang, MD, Mukharram M Bikbov, MD, Vinay Nangia, MD, Prof Jost B Jonas, MD, Yen-Po Chen, MD, Prof Wei-Chi Wu, MD, Prof Kyoko Ohno-Matsui, MD, Tyler Hyungtaek Rim, MD, Yih-Chung Tham, PhD, Rick Siow Mong Goh, PhD, Prof Haotian Lin, MD, Hanruo Liu, MD, Prof Ningli Wang, MD, Prof Weihong Yu, MD, Prof Donald Tiang Hwee Tan, FRCS (Ed), Prof Leopold Schmetterer, PhD, Prof Ching-Yu Cheng, MD, Prof Youxin Chen, MD, Chee Wai Wong, MBBS, Prof Gemmy Chui Ming Cheung, FRCOphth, Prof Seang-Mei Saw, PhD, Prof Tien Yin Wong, MD, Yong Liu, PhD, Daniel Shu Wei Ting, MD. “Retinal photograph-based deep learning algorithms for myopia and a blockchain platform to facilitate artificial intelligence medical research: a retrospective multicohort study”, The Lancet Digital Health. VOLUME 3, ISSUE 5, E317-E329, MAY 01, 2021. [Article]

    • Yih-Chung Tham, Ayesha Anees, Liang Zhang, Jocelyn Hui Lin Goh, Tyler Hyungtaek Rim, Simon Nusinovici, Haslina Hamzah, Miao-Li Chee, Gabriel Tjio, Shaohua Li, Xinxing Xu, Rick Goh, Fangyao Tang, Carol Yim-Lui Cheung, Ya Xing Wang, Vinay Nangia, Jost B Jonas, Bamini Gopinath, Paul Mitchell, Rahat Husain, Ecosse Lamoureux, Charumathi Sabanayagam, Jie Jin Wang, Tin Aung, Yong Liu, Tien Yin Wong, Ching-Yu Cheng. "Referral for disease-related visual impairment using retinal photograph-based deep learning: a proof-of-concept, model development study". The Lancet Digital Health. VOLUME 3, ISSUE 1, E29-E40, JAN 01, 2021. [Article]

  • Dan Milea, Raymond P.Najjar, Jiang Zhubo, Daniel Ting, Caroline Vasseneix, Xinxing Xu, Masoud Aghsaei Fard, Pedro Fonseca, Kavin Vanikieti, Wolf A Lagreze, Chiara La Morgia, Carol Y Cheung, Steffen Hamann, Christophe Chiquet, Nicolae Sanda, Hui Yang, Luis J Mejico, Marie-Benedicte Rougier, Richard Kho, Thi HC Tran, Shweta Singhal, Philippe Gohier, Catherine Clermont-Vignal, Ching-Yu Cheng, Jost B Jonas, Patrick Yu-Wai-Man, Clare L Fraser, John J Chen, Selvakumar Ambika, Neil R Miller, Yong Liu, Nancy J Newman, Tien Y Wong, Valerie Biousse. “Artificial Intelligence to Detect Papilledema from Ocular Fundus Photographs”, New England Journal of Medicine (NEJM) 382 (18), 1687-1695. Published in 30 April 2020. Impact Factor: 70.6. [Article] [Supplementary] [EDITORIAL][Media Report]

  • Daniel S. W. Ting, Yong Liu, Philippe Burlina, Xinxing Xu, Neil M. Bressler, Tien Y. Wong. AI for medical imaging goes deep. Nature Medicine 24, 539–540 (2018). [Link]

    • Shaohua Li, Xinxing Xu, Liqiang Nie, Tat-Seng Chua: Laplacian-Steered Neural Style Transfer. ACM Multimedia (ACM MM), Mountain View, CA USA, Oct 2017. [PDF]

  • Yong Kiam Tan, Xinxing Xu, Yong Liu: Improved Recurrent Neural Networks for Session-based Recommendations. The 1st workshop on Deep Learning for Recommender Systems (DLRS) at the 10th ACM Conference on Recommender Systems (RecSys). Boston, USA, Sept. 2016. [PDF]

  • Xinxing Xu, Joey Tianyi Zhou, IvorW. Tsang, Zheng Qin, Rick Siow Mong Goh, Yong Liu: Simple and Efficient Learning using Privileged Information. BeyondLabeler: Human is More Than a Labeler, Workshop of the 25th International Joint Conference on Artificial Intelligence (IJCAI-16). New York City, USA. July, 2016. [PDF_V1] [PDF_V2]. 2016 Best Paper Award, Contributed Talk.

  • A simple but extremely fast solution for SVM+ by utilizing the squared hinge loss instead of the square loss in the objective function, leading to up to hundred times speed up for SVM+.

  • Joey Tianyi Zhou, Xinxing Xu, Sinno Jialin Pan, Ivor W. Tsang, Qin Zheng and Rick Goh. Transfer Hashing with Privileged Information. In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI-16). New York City, USA. July 9-15, 2016. [PDF]

  • Li Niu, Xinxing Xu, Lin Chen, Lixin Duan, Dong Xu: Action and Event Recognition in Videos by Learning from Heterogeneous Web Sources. To Appear in IEEE Trans. Neural Netw. Learning Syst. (T-NNLS) [PDF].

  • A novel multi-domain adaptation method based on Elastic-net like Multiple Kernel Learning algorithm by learning from multiple heterogeneous web sources (i.e., Google/Bing Images, Flickr Videos) for video action (e.g., Hollywood2) and event recognition (e.g., CCV).

  • Xinxing Xu, Wen Li, Dong Xu, Ivor W. Tsang: Co-Labeling for Multi-view Weakly Labeled Learning. IEEE Trans. Pattern Anal. Mach. Intell. 38(6): 1113-1125 (2016). (T-PAMI) [PDF]

  • A novel unified weakly labelled multi-view learning framework using Multi-layer (i.e., 2-layer and 3-layer) Multiple Kernel Learning for Multi-view Semi-supervised learning, Multi-view Multi-instance learning and Multi-view relative outlier detection.

  • Xinxing Xu, Wen Li, Dong Xu: Distance Metric Learning Using Privileged Information for Face Verification and Person Re-Identification. IEEE Trans. Neural Netw. Learning Syst. 26(12): 3150-3162 (2015). (T-NNLS).

  • A novel Information-theoretic Metric Learning using Privileged Information (ITML+) algorithm for RGB face verification and person re-identification by learning from RGB-D data with additional privileged depth information in the training set.

    • Shengye Yan, Xinxing Xu, Dong Xu, Stephen Lin, and Xuelong Li: Image Classification with Densely Sampled Image Windows and Generalized Adaptive Multiple Kernel Learning. IEEE Transactions on Cybernetics, 45(3): 395-404 (2015). (T-CYB)

  • A Generalized Adaptive Multiple Kernel Learning algorithm by fusing visual features as well as decision features.

  • Shengye Yan, Xinxing Xu, Qingshan Liu: Learning the object location, scale and view for image categorization with adapted classifier. Information Sciences. March, 2014.

  • Xinxing Xu, Ivor W. Tsang and Dong Xu: Soft Margin Multiple Kernel Learning. IEEE Trans. Neural Netw. Learning Syst., vol. 24, no. 5, pp. 749–761, 2013. (T-NNLS) [PDF] [Code]. A new box constrained Multiple Kernel Learning objective and algorithm.

  • A novel Soft Margin framework for Multiple Kernel Learning, unifying, explaining the existing MKL formulations from the margin loss perspective and devising a new regularizer for MKL.

  • Xinxing Xu, Ivor W. Tsang and Dong Xu: Handling Ambiguity via Input-Output Kernel Learning, IEEE Int. Conf. on Data Mining (ICDM), December 2012, pp. 725-734. [PDF] (Full paper, Acceptance rate = 11%)

  • A unified Input-Output Kernel Learning (IOKL) framework based on Group Sparse (2-layer) Multiple Kernel Learning for Multiple Kernel Multiple Instance Learning, Multiple Kernel Semi-supervise Learning, Multiple Kernel Maximum Margin Clustering.

    • Shengye Yan, Xinxing Xu, Dong Xu, Stephen Lin and Xuelong Li: Beyond Spatial Pyramids: A New Feature Extraction Framework with Dense Spatial Sampling for Image Classification, European Conference on Computer Vision (ECCV), 2012

      • [PDF] Multiple Kernel Learning for Caltech256 and 15Scenes.

  • Dong Xu, Yi Huang, Zinan Zeng, Xinxing Xu: Human Gait Recognition Using Patch Distribution Feature and Locality-Constrained Group Sparse Representation. IEEE Transactions on Image Processing (T-IP) 21(1): 316-326 (2012). [PDF]

    • A new patch distribution feature (i.e., referred to as Gabor-PDF), which concatenates the Gabor features together with the X-Y coordinates

    • A new classification method called locality-constrained group sparse representation (LGSR), which incoporates both the group sparsity and local smoothness for sparse representation

  • Xinxing Xu, Dong Xu, Ivor W. Tsang: Video Concept Detection Using Support Vector Machine with Augmented Features. Proceedings of the Fourth Pacific-Rim Symposium on Image and Video Technology(PSIVT2010). [PDF]

    • An extremely simple but effective AFSVM, which transfers the knowledge across different semantic classes.

Surveys:

Useful Links:

Machine Learning Tutorials

Deep Reinforcement Learning (David Silver)

Deep Reinforcement Learning Papers

Computer Vision: Object Detection

Xinxing Xu (徐新兴)

Scientist, Team Lead, Computing & Intelligence Department

Institute of High Performance Computing (IHPC)

Adjunct Assistant Professor, Duke-NUS Medical School, National University of Singapore