Homepage of Xulei Yang
I am currently a Principal Scientist and Group Leader in Institute for Infocomm Research (I2R), A*STAR Singapore, previously the Head of Research in YITU Technology Singapore.
My research interests include:
- 3D Scene Understanding
- Biomedical & Biological Data Analysis
- Deep Learning for Computer Vision
📢 Openings
- Multi-modal Learning for 3D Scene Understanding (The goal of multi-modal learning is to fuse the advantage properties from each modality to complement each other and achieve comprehensive understanding of 3D scenes.)
- Robust Learning for 3D Scene Understanding (The goal of robust learning is to solve the imperative problems of scene understanding in real-world environments that usually are not independent and identically distributed or stationary.)
đź“ş News
- 2024.9: One paper was accepted by NeurIPS 2024.
- 2024.9: We are calling for paper submission to BlockSys’2025. Serving as the Industrial Chair.
- 2024.7: Two papers were accepted by ITSC 2024.
- 2024.7: One paper was accepted by ACM MM 2024.
- 2024.7: Two papers were accepted by ECCV 2024.
- 2024.6: Two papers were accepted by MICCAI 2024.
- 2024.4: Four papers were accepted by EMBC 2024.
- 2024.4: One paper was accepted by IEEE TNNLS.
- 2024.3: One paper was accepted by CVPR 2024.
- 2024.2: Our book “Deep Learning for 3D Vision: Algorithms and Applications” will be published soon by World Scientific Publishing, refer to announce and preface for the preview of this book.
- 2024.2: We are calling for paper submission to ICNC-FSKD 2024. Serving as the Proceedings Chair.
- 2024.1: One paper was accepted by Scientific Reports, link
- 2023.12: Our proposal CARDIA-GM has been awarded for Venture Exploration Workshop (Phase I) by SMART Innovation 2.0 Grant
- 2023.10: One paper was accepted by IEEE Network
- 2023.10: One paper was accepted by IEEE TCE
- 2023.8: One paper was accepted by IEEE JSAC
- 2023.7: Three papers were accepted by ICIP 2023.
- 2023.6: We are calling for paper submission to ICDM 2023 Workshop Machine Learning for Cybersecurity (MLC)
- 2023.5: We are calling for the support of Industry Sponsorship of IEEE 6th International Conference on Multimedia Information Processing and Retrieval MIPR 2023
- 2023.4: One paper was accepted by IJCAI 2023.
- 2023.4: We are hiring research scientists (PhD) and engineers (non-PhD) to work on deep learning for 3D vision. 🔥🔥🔥 Refer to Job Openings for the details.
- 2023.3: Our MTC programmatic proposal got approved [Lead PI, SGD 10M], the credit goes to the team!
đź“ť Publications
- G Rui, W Liu, Z GU, X Yang, J Cheng, Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching, CVPR 2024
- S Zhao, X Yang*, Z Zeng, et. al, Deep learning based CETSA feature prediction cross multiple cell lines with latent space representation, Scientific Reports, 2024
- C Li, Y Peng, G Liu, Y Li, X Yang, L Zhang, C Chen, Efficient Vision Transformer for Human-Centric AIoT Applications Through Token Tracking Assignment, IEEE Transactions on Consumer Electronics, 2023
- C Chen, Y Li, Q Wang, X Yang, X Wang, LT Yang, An Intelligent Edge-Cloud Collaborative Framework for Communication Security in Distributed Cyber-Physical Systems, IEEE Network, 2023
- M. Li, C. Chen, X Yang, J. Zhou, T. Zhang, Y. Li, Towards Communication-efficient Digital Twin via AI-powered Transmission and Reconstruction, IEEE Journal on Selected Areas in Communications, 2023
- R Sun, Z Zhao, L Shen, Z Zeng, Y Li, B Veeravalli, X Yang, An Efficient Deep Video Model For Deepfake Detection, IEEE International Conference on Image Processing (ICIP), 2023
- Z Cheng, C Chen, Z Zhao, P Qian, X Li, X Yang, COCO-TEACH: A Contrastive Co-Teaching Network For Incremental 3D Object Detection, IEEE International Conference on Image Processing (ICIP), 2023
- Q Wei, W Zheng, Y Li, Z Cheng, Z Zeng, X Yang, Controlling Facial Attribute Synthesis by Disentangling Attribute Feature Axes in Latent Space, IEEE International Conference on Image Processing (ICIP), 2023
- H Wang, X Yang, Efficient Practices for Profile-to-Frontal Face Synthesis and Recognition, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
- Z Zhao, P Qian, X Yang*, Z Zeng, C Guan, WL Tam, X Li, SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Efficient and Generalizable Protein–Protein Interaction Prediction, International Joint Conference on Artificial Intelligence (IJCAI), 2023
- Z Zhao, K Xu, HZ Yeo, X Yang, C Guan, MS-MT: Multi-Scale Mean Teacher with Contrastive Unpaired Translation for Cross-Modality Vestibular Schwannoma and Cochlea Segmentation, arXiv:2303.15826, 2023
- H Wang, H Zhang, L Yu, X Yang, Facial feature embedded CycleGAN for VIS–NIR translation, Multidimensional Systems and Signal Processing, 2023
- J Chen, Q Deng, X Yang, Non-cooperative game algorithms for computation offloading in mobile edge computing environments, Journal of Parallel and Distributed Computing, 2023
- X Zou, C Chen, X Yang, W Wei, K Li, DGSLN: Differentiable Graph Structure Learning Neural Network for Robust Graph Representations, Information Science, 2023
- Y Zhou, Z Huang, X Yang*, M Ang, TK Ng, GCM: Efficient Video Recognition with Glance and Combine Module, Pattern Recognition, 2023
🥇 Honors
- 2013-now Senior IEEE Member; 2017-now Kaggle Competition Master
2016-2018 Kaggle Competitions: 2 gold, 7 sliver, 2 bronze
- Intel & MobileOTD Cervical Cancer Screening, Rank 3rd/848 (USD10k), Top 1% - The Nature Conservancy Fisheries Monitoring, Rank 4th/2293 (USD20k), Top 1% - Dogs vs. Cats Redux: Kernels Edition, Rank 5th/1389, Top 1% - Planet: Understanding Amazon from Space, Rank 13th/938, Top 2% - Carvana Image Masking Challenge, Rank 13th/735, Top 2% - State Farm Distracted Driver Detection, Rank 14th/1440, Top 1% - Santander Value Prediction Challenge, Rank 36th/4477, Top 1% - Statoil/C-CORE Iceberg Classifier Challenge, Rank 39th/3449, Top 2% - Home Credit Default Risk, Rank 52th/7190, Top 1%
- 2015 Rakuten-Viki Global TV Recommender Challenge, 1st place (SGD8k)
đź’˛ Grants
Current (2021-now)
- Lead Principal Investigator , “Towards Realistic Deep Learning for 3D Vision”, MTC Programmatic Programme, approved.
- Co-Principal Investigator , “Label-efficient Meta-learning for Cross-domain Medical Image Segmentation”, AI3 HTPO Seed Fund (AI3 SF), kick-off soon
- Co-Principal Investigator , “Self-aware Continuously Learning Models”, AI Singapore Research Programme (AISG), 2022-2025
- Co-Principal Investigator (Team PI) , “A Protein Biophysical Strategy for Discovering and Targeting Key Protein Nodes in Cancer” Competitive Research Programme (CRP), 2020-2024
Previous (2014-2018)
- Co-Principal Investigator (Team PI) , “Intelligent Bioprocessing: Development of a Progressive Deep Machine Learning Framework towards Real-time Prediciton of Biologics Product Glycosylation”, SERC Strategic Funds (SSF), 2018-2019
- Principal Investigator , “Auto Graphical Prescription (Grx)”, ASTAR-GE Healthcare Collaboration Project, 2016-2017
- Co-Principal Investigator (Team PI) , “High Throughput Tissue-based Screening (HTTS): A Quantitative Approach to Increase Efficiency in Cancer Biomarkers Discovery and Translational Research”, Joint Council Office Project Fund (JCO), 2014-2017
- Co-Principal Investigator (Team PI) , “Deep Phenotyping Analysis of the Golgi: Automated In-depth Characterization of Image-based Phenotypes Scaled Up for Genome-wide Analysis of Golgi Regulatory Network”, Joint Council Office Project Fund (JCO), 2013-2016
đź“˝ Experiences
- Principal Scientist & Group Leader, I2R, ASTAR
- Head of Research, YITU Technology Singapore
- Scientist / Senior Scientist & Programme Head, IHPC/I2R, ASTAR
- Principal Engineer & 3D Vision Team Leader, GP Vision, MIT Semiconductor
- Senior / Principal Engineer & 2D Vision Team Leader, Zygo Vision Singapore
- PhD Student, NTU
- MEng & BEng, XJTU, China