About
I am an Assistant Professor in the School of Computer Science at University of Birmingham, where I lead the MIx (Machine Intelligence + x) group. I am also a Fellow of the Higher Education Academy (FHEA), and was a Royal Society Short Industry Fellow. Before joining Birmingham, I was fortunate to work as a Postdoctoral Researcher in the Biomedical Image Analysis (BioMedIA) group and the Visual Geometry Group (VGG) at the University of Oxford, advised by Prof Alison Noble and Prof Andrew Zisserman.
I obtained my PhD in Computer Science from City University of Hong Kong (supported by the Hong Kong PhD Fellowship), advised by Prof Qingxiong Yang and Prof Rynson W. H. Lau.
I have been lucky to work as a visiting scholar in the Image Formation and Processing(IFP) group at the University of Illinois Urbana-Champaign (UIUC), advised by Prof Thomas S. Huang. I was also lucky to work with Dr Linchao Bao as an intern at Tencent AI Lab.
My research interests include Computer Vision, Machine Learning, Healthcare, and AI4Science. I am particularly interested in learning representations in open world, by exploring auxiliary from different modalities and reducing the dependency on supervisions.
I am looking for self-motivated PhD students (as well as PostDoc, Master students, RAs, Visiting students/researchers, etc.). Please drop me an email with your CV if you are interested in working with me!
More details please find here.
News
Mar 2025: Our paper about incremental learning is accepted to CVPR 2025, congrats to the co-authors! Feb 2025: Will be serving as an Area Chair for NeurIPS 2025, and ACM Multimedia 2025. Feb 2025: Our paper about molecular structure prediction is accepted to The Journal of Physical Chemistry, congrats to Wenjin! Jan 2025: Our paper about open-world learning is accepted to ICLR 2025, congrats to Qiming! Dec 2024: Will be serving as an Area Chair for ICML 2025. Nov 2024: Very glad to receive the Best Paper Award at the MICAD 2024! Congrats to Kangning and the Team! Nov 2024: Great thanks to Meta Project Aria for their in-kind contributions, and honoured to be an Academic Partner! Oct 2024: Very glad to receive the Best Paper Award and Best Presentation (Runner-Up) Award at the MICCAI 2024 ASMUS Workshop! Congrats to Kangning and the Team! Sep 2024: Two papers (1 Spotlight) accepted to NeurIPS 2024 and one paper accepted to ACCV 2024, congrats to all the co-authors! Aug 2024: Will be serving as an Area Chair for ICLR 2025. Jul 2024: Our paper "Show from Tell" has been finally published in Scientific Reports (Nature Portfolio)! Please check it out here and here: https://rdcu.be/dNcmb :) Jul 2024: Three papers accepted to ECCV 2024, congrats to all the co-authors! Jul 2024: Two papers accepted to MICCAI Workshop and ACM MM 2024, congrats to all the co-authors! Mar 2024: Will be serving as an Area Chair for NeurIPS 2024. Mar 2024: Very grateful to be awarded the Amazon Research Award! Feb 2024: Will be serving as the Action Editor (AE) for The Transactions on Machine Learning Research, welcome submitting your ML research! Feb 2024: Two papers (a novel 360+x dataset (Oral Presentation, 3.3% of accepted papers), and a multiview 3D dataset DyMVHumans) accepted to CVPR 2024, congrats to all the co-authors! Feb 2024: One paper accepted to ISBI 2024 as Oral Presentation, and one paper accepted to T-IP, congrats to all the co-authors! Nov 2023: Glad to be recognised as a Top Reviewer by NeurIPS 2023. Oct 2023: Two papers are accepted to WACV 2024, congrats to all the co-authors! Oct 2023: Very glad to be recognised as an IEEE TMI Distinguished Reviewer Sep 2023: Grateful to be awarded the Royal Society Short Industry Fellowship! Aug 2023: One paper is accepted to IJCV. Congrats to all the co-authors! Jul 2023: Four papers are accepted to ICCV 2023. Congrats to all the co-authors (esp. my MSc students Hao and Chenyuan)! Apr 2023: Grateful to receive the International Exchanges Grant from The Royal Society! Apr 2023: Two papers are accepted to CVPR 2023 Workshops (Foundation Model and Sight and Sound) about self-supervised multi-modal (video-text-audio) representation learning Mar 2023: Two papers are accepted to ICLR 2023 workshops (TML4H and Neural Fields) about medical video quality assessment and neural representations in low-level vision. Congrats to Jong and my MSc student Wentian! Jan 2023: Will join the editorial board of Springer The Visual Computer Journal (TVCJ) as an Associate Editor, please consider submit your work! Dec 2022: Very glad to be recognised as an Outstanding Reviewer by ACCV 2022 Dec 2022: Will join the editorial board of IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT) as the Associate Editor, please consider submit your work to T-CSVT! Oct 2022: Very glad to receive the Best Paper Award at the ECCV 2022 Workshop on Medical Computer Vision! Congrats to the PULSENet Team! Sep 2022: One paper is accepted to NeurIPS 2022 about continual learning Aug 2022: One paper is accepted to ECCV 2022 Workshop (ECCV-MCV) about anatomy-aware contrastive medical representation learning Jul 2022: Proud to receive the Outstanding Reviewer Award (top 10%) from ICML 2022 Feb 2022: Will be serving as an Area Chair for ACM MM 2022, please consider contributing your work to the conference! Feb 2022: I joined the University of Birmingham as an Assistant Professor Oct 2021: One paper is accepted to NeurIPS 2021 Workshop (MedNeurIPS) about explainability of self-supervised learning in medical imaging Oct 2021: One paper is accepted to BMVC 2021 about achieving equivariance to transformations in deep networks Oct 2021: Proud to receive the Outstanding Reviewer Award (top 8%) from NeurIPS 2021 Sep 2021: One paper is accepted to NeurIPS 2021 about self-supervised visual representation learning via implicitly borrowing attention from transformers Jul 2021: One paper is accepted to ICCV 2021 Jun 2021: Proud to be an Outstanding Reviewer for CVPR 2021 May 2021: One paper accepted to T-PAMI, in which we show state-of-the-art performance on weakly-supervised semantic segmentation across different supervision levels Jan 2021: One paper accepted to T-PAMI, with state-of-the-art performance on self-supervised video representation learning Nov 2020: Will be serving as a Senior PC for IJCAI 2021 Oct 2020: Proud to be an Outstanding Reviewer for MICCAI 2020 Jun 2020: Proud to be an Outstanding Reviewer for ECCV 2020
Revisit the Open Nature of Open Vocabulary Semantic Segmentation
CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation
Transformer-Based Models for Predicting Molecular Structures from Infrared Spectra Using Patch-Based Self-Attention
PRFormer: Matching Proposal and Reference Masks by Semantic and Spatial Similarity for Few-Shot Semantic Segmentation
360+x: A Panoptic Multi-modal Scene Understanding Dataset
Show from Tell: Audio-Visual Modelling in a Clinical Setting
Out-of-Clinical-Distribution Detection with a Softmax-Conditioned Variational Autoencoder Regulariser: Application to Fetal Ultrasound
Few Exemplar-Based General Medical Image Segmentation via Domain-Aware Selective Adaptation
Bridge the Points: Graph-based Few-shot Segment Anything Semantically
Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis
Disentangled Generation and Aggregation for Robust Radiance Fields
MVPGS: Excavating Multi-view Prior for Gaussian Splatting from Sparse Input Views
Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction
Fetal Ultrasound Video Representation Learning using Contrastive Rubik’s Cube Recovery
DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling
Disentangled Pre-training for Image Matting
FreMIM: Fourier Transform Meets Masked Image Modeling for Medical Image Segmentation
Frame Interpolation with Consecutive Brownian Bridge Diffusion
Surface-SOS: Self-Supervised Object Segmentation via Neural Surface Representation
Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation
Dual Representation Learning from Fetal Ultrasound Video and Sonographer Audio
Inferring Attention Shifts for Salient Instance Ranking
Multi-view Self-supervised Disentanglement for General Image Denoising
CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation
CL-MVSNet: Unsupervised Multi-view Stereo with Dual-level Contrastive Learning
Diffuse3D: Wide-Angle 3D Photography via Bilateral Diffusion
Bridging the Gap: Cross-modal Knowledge Driven Network for Radiology Report Generation
Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training
Cali-NCE: Boosting Cross-modal Video Representation Learning with Calibrated Alignment
Revisiting Implicit Neural Representations in Low-Level Vision
A Kernel Density Estimation based Quality Metric for Quality Assessment of Obstetric Ultrasound Video
Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation
Anatomy-Aware Contrastive Representation Learning for Fetal Ultrasound
Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks
Explainability of Self-Supervised Representation Learning for Medical Ultrasound Video
Self-Supervised Video Representation Learning by Uncovering Spatio-temporal Statistics
Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning
Scene Context-Aware Salient Object Detection
Facial Anatomical Landmark Detection using Regularized Transfer Learning with Application to Fetal Alcohol Syndrome Recognition
Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
Multi-View Face Synthesis via Progressive Face Flow
Self-Supervised Contrastive Video-Speech Representation Learning for Ultrasound
Unified Image and Video Saliency Modeling
Self-Supervised Video Representation Learning by Pace Prediction
Self-Supervised Ultrasound to MRI Fetal Brain Image Synthesis
Self-Supervised Representation Learning for Ultrasound Video
Tactile Sketch Saliency
Inferring Attention Shift Ranks of Objects for Image Saliency
When AWGN-based Denoiser Meets Real Noises
Cross-Task Representation Learning for Anatomical Landmark Detection
Differentiating Operator Skill During Routine Fetal Ultrasound Scanning Using Probe Motion Tracking
FormNet: Formatted Learning for Image Restoration
Connecting Image Denoising and High-Level Vision Tasks via Deep Learning
Anatomy-Aware Self-Supervised Fetal MRI Synthesis from Unpaired Ultrasound Images
Geometry-Aware Distillation for Indoor Semantic Segmentation
Self-Supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
Ground-Aware Point Cloud Semantic Segmentation for Autonomous Driving
Few-shot Breast Cancer Metastases Classification via Unsupervised Cell Ranking
Stereoscopic Image Generation from Light Field with Disparity Scaling and Super-Resolution
Referring Image Segmentation by Generative Adversarial Learning
Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss
Task-Driven Webpage Saliency
Delving into Salient Object Subitizing and Detection
Joint Image Denoising and Disparity Estimation via Stereo Structure PCA and Noise-Tolerant Cost
FormResNet: Formatted Residual Learning for Image Restoration
A Hand Pose Tracking Benchmark From Stereo Matching
Color Image Guided Boundary-inconsistent Region Refinement for Stereo Matching
Local Stereo Matching with Improved Matching Cost and Disparity Refinement
Cost-Volume Filtering-Based Stereo Matching with Improved Matching Cost and Secondary Refinement
![[Poster]](srcs/medneurips_poster.jpeg){kind=link}