I am a Lecturer (Assistant Professor) affiliated with the Vision, Learning, and Control (VLC) group in the School of Electronics and Computer Science (ECS) at the University of Southampton.
I specialize in computer vision and machine learning for artificial general intelligence. I am committed to teaching AI/machines to comprehend the world through multimodal data, enabling them to achieve animal-level, or human-level, or superhuman-level general intelligence. My current focus is on making machine learning models more capable and controllable to understand the physical world, through scaling and aligning compute, data, models, and tasks for deep learning. I am interested in exploring machine learning methodologies, including generative modeling, continual learning, and affective computing.
News
10/2023, We have openings for PhD positions: 'Generative Modeling in Computer Vision' and 'Deepfake Detection with Continual Learning'. Note that these positions are open to students from UK and Horizon Europe qualifying countries (meeting the criteria for UK home-level fees) as well as other international students.
02/2023, We are opening some positions for talents who are keen to publish papers, open source code, and make an impact.
02/2023, One interesting paper "Freestyle Layout-to-Image Synthesis" is accepted as a highlight (10% of accepted papers, 2.5% of submissions) to CVPR 2023. This paper introduces freestyle layout-to-image synthesis with diffusion generative network (FreestyleNet). The proposed FreestyleNet produces realistic-looking and creative images like ‘a warehouse running on a railroad’ and 'a hornless unicorn sitting on a bench'. Thanks all the reviewers for valuable comments and constructive suggestions!
01/2023, I join University of Southampton as a Lecturer (Assistant Professor) in Computer Science.
11/2022, One paper "An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement" gets accepted to IJCV.
11/2022, Two papers "Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference" and "Riemannian Local Mechanism for SPD Neural Networks" are accepted at AAAI 2023.
10/2022, One paper "Multi-agent Actor-Critic with Time Dynamical Opponent Model" gets accepted to Neurocomputing.
09/2022, One inspiring 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 continual learning paradigm (S-Prompts). 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 Singapore as a tenure-track Assistant Professor in Computer Science.
more news...
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
11/2018, One paper "Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets" is accepted by AAAI 2019. This paper applies the theory of optimal transport on non-compact manifolds from Alessio Figalli (2018 Fields Medal winner) to generative modeling, which is able to generate photo-realistic biological samples.
07/2018, One paper "Wasserstein Divergence for GANs" is accepted by ECCV 2018.
04/2018, One paper "Covariance Pooling for Facial Expression Recognition" is accepted by the workshop DiffCVML in CVPR 2018.
11/2017, One paper "Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video" is accepted as a Regular Paper in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
11/2017, One paper "Building Deep Networks on Grassmann Manifolds" (GrNet) is accepted by AAAI 2018.
08/2017, One paper "Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition with Image Sets" is accepted by IEEE Transactions on Image Processing (TIP).
07/2017, One paper "Geometry-aware Similarity Learning on SPD Manifolds for Visual Recognition" is accepted by IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).
02/2017, One paper "Deep Learning on Lie Groups for Skeleton-based Action Recognition" (LieNet) is accepted as a spotlight by CVPR 2017. This paper proposes deep networks of Lie Groups for skeleton-based action recognition.
11/2016, One paper "A Riemannian Network for SPD Matrix Learning" (SPDNet) is accepted by AAAI 2017. This paper opens a new direction of deep manifold networks.
09/2015, I join ETH Zurich as a Postdoc Researcher in Computer Vision Lab.
|