associate professor at Universiti Malaya

Google Scholar | [Curriculum Vitae]
Follow @cs-chan

My research interests include computer vision and machine learning with focus on scene understanding. I am also interested in the interplay between language and vision: generating sentential descriptions about complex scenes. I was the founding Chair for the IEEE Computational Intelligence Society (CIS) Malaysia chapter, the organising chair for ACPR in 2015, and general chair for MMSP in 2019 & VCIP in 2013. I am a Senior Member of IEEE, a Chartered Engineer and a Member of IET.

        10/2021: Two(2) papers accepted in PR.
        09/2021: One(1) paper to appear in NeurIPS-2021.
        08/2021: We host a workshop at IJCAI, 2021 - Toward Intellectual Property Protection on Deep Learning as a Services.
        06/2021: One(1) paper accepted in T-PAMI.
        06/2021: One(1) paper to appear in MIUA-2021 (Best Student Paper Award).
        05/2021: One(1) paper to appear in ICIP-2021.
        03/2021: One(1) paper to appear in CVPR-2021.
        02/2021: We organise a real world problem-solving competition on Integrated Circuit OCR in ICDAR-2021.

I am always interested to hear from prospective research students. Scholarships are available from time to time, contact me to enquire.

Latest Works


One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective Star

This paper proposes a novel deep hashing model with only a single learning objective which is a simplification from most state of the art papers generally use lots of losses and regularizer.

J.T. Hoe, K.W. Ng, T. Zhang, C.S. Chan, Y-Z. Song and T. Xiang
NeurIPS 2021 (acceptance rate: 2372/9122 ~ 26.0%)
[pdf] [code]


D’OraCa: Deep Learning-Based Classification of Oral Lesions with Mouth Landmark Guidance for Early Detection of Oral Cancer

We develop a novel deep learning framework named D’OraCa to classify oral lesions using photographic images.

J.H. Lim, C.S, Tan, C.S. Chan et al.
MIUA 2021 (Best Student Paper Award)


DeepIP: Deep Neural Network Intellectual Property Protection with Passports Star

We propose novel passport-based DNN ownership verification schemes which are both robust to network modifications and resilient to ambiguity attacks (i.e. the DNN model performance of an original task will be significantly deteriorated due to forged passports). Extension of NeurIPS 2019 (acceptance rate: 1428/6743 ~ 21.18%).

L. Fan, K.W. Ng, C.S. Chan and Q. Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence (in Press)
[pdf] [code]


From Gradient Leakage to Adversarial Attacks in Federated Learning Star

This paper aims to cast the doubts towards the reliability of the DNN with solid evidence particularly in Federated Learning environment by utilizing an existing privacy breaking algorithm which inverts gradients of models to reconstruct the input data.

J.Q. Lim and C.S. Chan
ICIP 2021
[pdf] [poster]


Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attacks Star

This paper presents a complete protection framework in both black-box and white-box settings to enforce IPR protection on GANs.

D.S. Ong, C.S. Chan, K.W. Ng, L. Fan and Q. Yang.
CVPR 2021 (acceptance rate: 1663/7015 ~ 23.7%)
[pdf] [code]