I am an Assistant Professor of Computer Science in the School of Computing and Information Systems at Singapore Management University (SMU)
. Before coming to Singapore, I worked as a Guest/Postdoc Researcher with Prof. Luc Van Gool
in Computer Vision Lab
at ETH Zurich
. My SAVG
(SMU Autonomous Vision Group) researches autonomous visual computing that aims for making machines to learn the visual world, all by themselves. Our current research focuses on visual deepfake, affective and behavior computing through automated machine learning on data, label, feature, neuron and task. Our ultimate quest is artificial general intelligence with rational, emotional and imaginal capabilities.
I am looking for motivated and talented PhD students to join my research group. Please follow the instructions to reach me if you are interested.
09/2022, One paper "S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning" gets accepted to NeurIPS 2022. This paper proposes a rule-breaking paradigm (S-Prompting) for domain incremental learning. It does not require the accumulation of the knowledge from previously learned domains. Instead, it merely learns the knowledge independently domain by domain, through simply prompting the state-of-the-art transformers.
08/2022, One paper "A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials" gets accepted to WACV 2023.
06/2022, One paper "Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution" is accepted by the CVPR-2022 NAS workshop.
03/2022, One paper "Generative Flows with Invertible Attentions" is accepted by CVPR 2022, with surprisingly increased final review scores (2 strong accepts and 2 borderline accepts). Thanks all the reviewers for the valuable comments and suggestions! This paper introduces an interesting idea of Invertible Transformer-based Attentions to Generative Normalizing Flows.
10/2021, One paper "Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo" is accepted by WACV 2022.
09/2021, I join SMU as a tenure-track Assistant Professor in Computer Science.
07/2021, One paper "Direct Differentiable Augmentation Search" is accepted by ICCV 2021.
04/2021, One paper "Neural Architecture Search of SPD Manifold Networks" is accepted by IJCAI 2021.
03/2021, Two papers "Efficient Conditional GAN Transfer with Knowledge Propagation across Classes" and "GANmut: Learning Interpretable Conditional Space for Gamut of Emotions" are accepted by CVPR 2021.
01/2021, One paper "Spectral Tensor Train Parameterization of Deep Learning Layers" is accepted by AISTATS 2021.
12/2020, One paper "Neural Architecture Search as Sparse Supernet" is accepted by AAAI 2021.
11/2020, One paper "Facial Emotion Recognition with Noisy Multi-task Annotations" is accepted by WACV 2021.
08/2020, One paper "AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results" will appear at the workshop AIM in conjunction with ECCV 2020.
07/2020, One paper "Weakly Paired Multi-Domain Image Translation" is accepted by BMVC 2020 as an oral.
07/2020, One paper "Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search" is accepted by ECCV 2020.
05/2020, We are organizing AIM Video Super-Resolution Challenge @ECCV 2020.
05/2020, One paper "NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results" will appear at the workshop NTIRE in conjunction with CVPR 2020.
12/2019, We are organizing NTIRE Video Quality Mapping Challenge @CVPR 2020.
10/2019, One dataset paper "The Vid3oC and IntVID Datasets for Video Super Resolution and Quality Mapping" will appear at the workshop AIM in ICCV 2019.
10/2019, We are organizing a workshop "AIM: Advances in Image Manipulation Workshop and Challenges on Image and Video Manipulation"
and a tutorial "FIRE: From Image Restoration to Enhancement and Beyond" at ICCV, Oct. 27, 2019.
02/2019, One paper "Sliced Wasserstein Generative Models" is accepted by CVPR 2019. This paper was selected as one of the best publications of the week (20.04.2019), by DeepAI. Link to DeepAI Website