My research interests include computer vision and machine learning, where I lead a young and energetic research team that has published more than 100 papers in related top peer-review conferences and journals (e.g. CVPR, NeurIPS, TPAMI, TIP etc). I was the founding Chair for IEEE Computational Intelligence Society, Malaysia chapter.
Also currently, I serve as the Associate Editor of Pattern Recognition (Elsevier), and have co-organized several conferences/workshops/tutorials/challenges related to computer vision/machine learning. I was the recipient of Top Research Scientists Malaysia (TRSM) in 2022, Young Scientists Network Academy of Sciences Malaysia (YSN-ASM) in 2015 and Hitachi Research Fellowship in 2013. Besides that, I am also a senior member (IEEE), Professional Engineer (BEM) and Chartered Engineer (IET).
During 2020-2022, I was seconded to the Ministry of Science, Technology and Innovation (MOSTI) as the Lead of PICC Unit under COVID19 Immunisation Task Force (CITF), as well as the Undersecretary for Division of Data Strategic and Foresight.
Highlights:
02/2024: One(1) paper to appear in CVPR-2024. Please see Project Page.
08/2023: One(1) paper (oral) to appear in BMVC-2023. Please see Project Page.
professor at Universiti Malaya
Latest Works
InteractDiffusion: Interaction-Control for Text-to-Image Diffusion Model Star
J.T. Hoe, X. Jiang, C.S. Chan, Y-P. Tan and W. Hu
CVPR 2024 (acceptance rate: 2719/11532 ~ 23.6%)
Existing methods lack ability to control the interactions between objects in the generated content. This paper proposes a pluggable interaction control model, called InteractDiffusion that extends existing pre-trained T2I diffusion models to enable them being better conditioned on interactions.
pdf code video demoSFAMNet: A scene flow attention-based micro-expression network Star
G-B. Liong, S-T. Liong, C.S. Chan and J. See
Neurocomputing (2024)
This paper proposes the first Scene Flow Attention-based Micro-expression Network, namely SFAMNet. Extensive experiments performed on three tasks: (i) ME spotting; (ii) ME recognition; and (iii) ME analysis on the multi-modal CAS(ME)^3 dataset indicate that depth is vital in capturing the ME information.
pdf codeUnsupervised Hashing with Similarity Distribution Calibration Star
K.W. Ng, X. Zhu, J.T. Hoe, C.S. Chan, T. Zhang, Y-Z. Song and T. Xiang
BMVC 2023 (oral, acceptance rate: ~ 7.5%)
This paper proposes Similarity Distribution Calibration (SDC) method to align the hash code similarity distribution towards a calibration distribution (e.g., beta distribution) with sufficient spread across the entire similarity range, in order to alleviate the similarity collapse problem.
pdf slide codeCycle-object consistency for image-to-image domain adaptation Star
C-T. Lin, J-L. Kew, C.S. Chan, S-H. Lai and C. Zach
Pattern Recognition (2023)
This work is focused on image2image domain adaptation (see pic beside) where we introduced an instance-aware GAN framework, AugGAN-Det, to jointly train a generator with an object detector (for image object style) and a discriminator (for global style).
pdf