TOP: We are always looking for highly self-motivated students. Please contact me if you wish to consider
short-term internship with paid allowance & eligible to non-Singaporean undergrad and master students.
visiting PhD/Master/Ungrad funded by
CSC,
ARAP and
SIPGA scholarships are available.
pursuing PhD with Singapore universities and A*STAR funded by
SINGA or
ARAP scholarship.
Find more details for eligible
scholarships
12nd May 2023:
OPENING (DDL: open until filled): One full-time
research scientist position on developing robust 3D deep learning algorithms is available with
details. Please contact me for informal inquiries.
2nd May 2023:
OPENING (DDL: open until filled): One
PhD full scholarship (ARAP) starting from Sep 2023 jointly supported by A*STAR and University of Surrey is available.
Prof. Xiatian Zhu will be the host supervisor at Surrey. Please contact me and/or Prof. Zhu for the position.
Feb 2023:
OPENING (DDL: 13th May): One PhD full scholarship (ARAP) starting from Sep 2023 jointly supported by A*STAR and University of Coventry is available. Pleas find more details
here.
May 2023:
A*STAR MTC Programmatic Fund "Towards Realistic Deep Learning for 3D Vision" (SGD$ 1.1M allocated) will kickstart in Aug 2023
- We shall develop 3D deep learning techniques robust to imperfect visibility, adversarial attacks and incremental data to enable deployment in real-world applications.
Sep 2022: Our work on
Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering was accepted by NeurIPS 2022. Congratulations to
Su Yongyi!
Jun 2022: Our work on
Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding was accepted by ICPR 2022 as Oral presentation.
May 2022: Two works to appear in IEEE Transactions on Image Processing (TIP).
Nov 2021: Our work on
Automatic Data Augmentation for 3D Point Cloud has appeared in BMVC 2021. Code is available
here.
Jun 2021: The first 3D affordance prediction dataset
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding has appeared in CVPR 2021. Code is available
here.
May 2021:
A*STAR CDA Project "Exploiting Unlabeled Data, Cheaper Labels and Efficient Annotation for 3D
Point Cloud Deep Learning" (EUDEA) ($SGD 238k allocated)
- My project on exploring label-efficient learning on 3D point cloud data started from Apr. 2021.
- We will be looking into improving the efficiency of 3D point cloud learning from several perspectives.