Publications

Summary: CVPR/ICCV/ECCV (16), AAAI/IJCAI/ACM MM (8), TPAMI (3), IEEE Transactions (20).
^ joint first authors; * corresponding author

2025

  • Demystify Transformers & Convolutions in Modern Image Deep Networks
    Xiaowei Hu^, Min Shi^, Weiyun Wang^, Sitong Wu^, Linjie Xing, Wenhai Wang, Xizhou Zhu, Lewei Lu, Jie Zhou, Xiaogang Wang, Yu Qiao, and Jifeng Dai*
    IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), vol. 47, no. 4, pp. 2416-2428, 2025.
    [paper] [arXiv] [code]

  • Fast Image Super-Resolution via Consistency Rectified Flow
    Jiaqi Xu, Wenbo Li, Haoze Sun, Fan Li, Zhixin Wang, Long Peng, Jingjing Ren, Haoran Yang, Xiaowei Hu, Renjing Pei, and Pheng-Ann Heng
    IEEE International Conference on Computer Vision (ICCV), accepted, 2025.

  • EchoTraffic: Enhancing Traffic Anomaly Understanding with Audio-Visual Insights
    Zhenghao Xing^, Hao Chen^, Binzhu Xie, Jiaqi Xu, Ziyu Guo, Xuemiao Xu, Jianye Hao, Chi-Wing Fu, Xiaowei Hu*, and Pheng-Ann Heng
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19098-19108, 2025.
    [paper] [code]

  • MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models
    Donghao Zhou^, Jiancheng Huang^, Jinbin Bai, Jiaze Wang, Hao Chen, Guangyong Chen, Xiaowei Hu*, and Pheng-Ann Heng
    International Joint Conference on Artificial Intelligence (IJCAI), accepted, 2025.
    [arXiv] [project]

  • Device-Cloud Collaborative Learning Framework for Efficient Unknown Object Detection
    Kewei Zhao, Xiaowei Hu, and Qinya Li
    ACM Multimedia (ACM MM), accepted, 2025.

  • Unifying Physically-Informed Weather Priors in A Single Model for Image Restoration Across Multiple Adverse Weather Conditions
    Jiaqi Xu, Xiaowei Hu*, Lei Zhu, and Pheng-Ann Heng
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), accepted, 2025.
    [paper]

  • Volumetric Medical Image Segmentation via Fully 3D Adaptation of Segment Anything Model
    Haoneng Lin, Jing Zou, Sen Deng, Ka Po Wong, Angelica I. Aviles-Rivero, Yiting Fan, Alex Pui-Wai Lee, Xiaowei Hu, and Jing Qin
    Biocybernetics and Biomedical Engineering, vol. 45, pp. 1-10, 2025.
    [paper]

  • Multi-Scale Contextual Learning for Medical Image Segmentation via Dual Distillationn
    Ruize Cui, Lanqing Liu, Youyi Song, Ge Ren, Xiaowei Hu*, and Jing Qin
    Medical Physics, vol. 52, no. 2, pp. 787-800, 2025.
    [paper]

  • A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
    Ming Hu et al.
    ArXiv Tech Report, 2025.
    [arXiv] [project]

2024

  • Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models
    Jiaqi Xu, Mengyang Wu, Xiaowei Hu*, Chi-Wing Fu, Qi Dou, and Pheng-Ann Heng
    European Conference on Computer Vision (ECCV), pp. 147-164, 2024
    [paper] [arXiv] [code]

  • Video Instance Shadow Detection Under the Sun and Sky
    Zhenghao Xing^, Tianyu Wang^, Xiaowei Hu*, Haoran Wu, Chi-Wing Fu, and Pheng-Ann Heng
    IEEE Transactions on Image Processing (IEEE TIP), vol. 33, pp. 5715-5726, 2024
    [paper] [arXiv] [project]

  • Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling
    Guoqi Yu, Jing Zou, Xiaowei Hu, Angelica I. Aviles-Rivero, Jing Qin, and Shujun Wang
    International Conference on Machine Learning (ICML), vol. 235, pp. 57818-57841, 2024
    [arXiv]

  • TrafficMOT: A Challenging Dataset for Multi-Object Tracking in Complex Traffic Scenarios
    Lihao Liu, Yanqi Cheng, Zhongying Deng, Shujun Wang, Dongdong Chen, Xiaowei Hu, Pietro Liò, Carola-Bibiane Schönlieb, and Angelica I. Aviles-Rivero
    ACM Multimedia (ACM MM), pp. 1265-1273, 2024
    [paper] [arXiv]

  • Semi-Supervised TEE Segmentation via Interacting with SAM Equipped with Noise-Resilient Prompting
    Sen Deng, Yidan Feng, Haoneng Lin, Yiting Fan, Alex Pui-Wai Lee, Xiaowei Hu, and Jing Qin
    AAAI Conference on Artificial Intelligence (AAAI), pp. 11757-11765, 2024
    [paper]

  • Dynamic Message Propagation Network for RGB-D and Video Salient Object Detection
    Baian Chen, Zhilei Chen, Xiaowei Hu, Jun Xu, Haoran Xie, Jing Qin, and Mingqiang Wei
    ACM Transactions on Multimedia Computing Communications and Applications (ACM TOMM), vol. 20, no. 1, pp. 1-21, 2024
    [paper] [arXiv]

  • Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era
    Xiaowei Hu^, Zhenghao Xing^, Tianyu Wang, Chi-Wing Fu, and Pheng-Ann Heng
    ArXiv Tech Report, 2024
    [arXiv] [project] [supp.] [report]

2023

  • Instance Shadow Detection with A Single-Stage Detector
    Tianyu Wang, Xiaowei Hu*, Pheng-Ann Heng, and Chi-Wing Fu
    IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), vol. 45, no. 3, pp. 3259-3273, 2023
    [paper] [arXiv] [code] [SOBA dataset]

  • SILT: Shadow-Aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels
    Han Yang^, Tianyu Wang^, Xiaowei Hu*, and Chi-Wing Fu
    IEEE International Conference on Computer Vision (ICCV), pp. 12687-12698, 2023
    [paper] [arXiv] [code] [SBU-Refine dataset]

  • Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions
    Yurui Zhu^, Tianyu Wang^, Xueyang Fu*, Xuanyu Yang, Xin Guo, Jifeng Dai, Yu Qiao, and Xiaowei Hu*
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21747-21758, 2023
    [paper] [code]

  • Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior
    Jiaqi Xu, Xiaowei Hu*, Lei Zhu*, Qi Dou, Jifeng Dai, Yu Qiao, and Pheng-Ann Heng
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18053-18062, 2023
    [paper] [arXiv] [code] [HazeWorld dataset] [report (zhihu)]

  • Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation
    Min Shi, Zihao Huang, Xianzheng Ma, Xiaowei Hu, and Zhiguo Cao
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7308-7317, 2023 (Highlight)
    [paper] [code]

  • InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
    Wenhai Wang, Jifeng Dai, Zhe Chen, Zhenhang Huang, Zhiqi Li, Xizhou Zhu, Xiaowei Hu, Tong Lu, Lewei Lu, Hongsheng Li, Xiaogang Wang, and Yu Qiao
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14408-14419, 2023 (Highlight)
    [paper] [arXiv] [code] [video]

  • IDRNet: Intervention-Driven Relation Network for Semantic Segmentation
    Zhenchao Jin, Xiaowei Hu, Lingting Zhu, Luchuan Song, Li Yuan, Lequan Yu
    Advances in Neural Information Processing Systems (NeurIPS), 2023
    [paper] [arXiv] [code]

  • Deep Texture-Aware Features for Camouflaged Object Detection
    Jingjing Ren^, Xiaowei Hu^, Lei Zhu, Xuemiao Xu, Yangyang Xu, Weiming Wang, Zijun Deng, and Pheng-Ann Heng
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), vol. 33, no. 3, pp. 1157-1167, 2023
    [paper] [arXiv]

  • Representative Feature Alignment for Adaptive Object Detection
    Shan Xu, Huaidong Zhang, Xuemiao Xu*, Xiaowei Hu*, Yangyang Xu, Liangui Dai, Kup-Sze Choi, and Pheng-Ann Heng
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), vol. 33, no. 2, pp. 689-700, 2023
    [paper]

  • Spectrum and Style Transformation Framework for Omni-Domain COVID-19 Diagnosis
    Zhenkun Wang, Shuangchun Gui, Xinpeng Ding, Xiaowei Hu*, Xiaowei Xu*, and Xiaomeng Li
    IEEE Transactions on Emerging Topics in Computational Intelligence (IEEE TETCI), vol. 7, no. 5, pp. 1527-1538, 2023
    [paper]

2022

  • Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection
    Tianyu Wang, Xiaowei Hu*, Zhengze Liu, and Chi-Wing Fu
    Advances in Neural Information Processing Systems (NeurIPS), 2022.
    [paper] [arXiv] [code]

  • Learning Shadow Correspondence for Video Shadow Detection
    Xinpeng Ding, Jingwen Yang, Xiaowei Hu, and Xiaomeng Li
    European Conference on Computer Vision (ECCV), pp. 705-722, 2022.
    [paper] [arXiv] [code]

  • Enhanced Coarse-to-Fine Network for Image Restoration
    Yurui Zhu, Xi Wang, Xueyang Fu*, and Xiaowei Hu*
    1st Mobile Intelligent Photography & Imaging Workshop @ ECCV 2022, pp. 130-146, 2022.
    [paper] [certificate] [code]

  • Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentation
    Huifeng Yao, Xiaowei Hu, and Xiaomeng Li
    AAAI Conference on Artificial Intelligence (AAAI), pp. 3099-3107, 2022.
    [paper] [arXiv] [code]

2021

  • Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
    Xiaowei Hu, Tianyu Wang, Chi-Wing Fu, Yitong Jiang, Qiong Wang, and Pheng-Ann Heng
    IEEE Transactions on Image Processing (IEEE TIP), vol. 30, pp. 1925-1934, 2021.
    [paper] [arXiv] [CUHK-Shadow dataset] [evaluation function] [code]

  • Single-Image Real-Time Rain Removal Based on Depth-Guided Non-Local Features
    Xiaowei Hu, Lei Zhu, Tianyu Wang, Chi-Wing Fu, and Pheng-Ann Heng
    IEEE Transactions on Image Processing (IEEE TIP), vol. 30, pp. 1759-1770, 2021.
    [paper] [code] [RainCityscapes dataset]

  • Single-Stage Instance Shadow Detection with Bidirectional Relation Learning
    Tianyu Wang^, Xiaowei Hu^*, Chi-Wing Fu, and Pheng-Ann Heng
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-11, 2021. (Oral)
    [paper] [supp.] [video] [code] [poster]

  • SAC-Net: Spatial Attenuation Context for Salient Object Detection
    Xiaowei Hu, Chi-Wing Fu, Lei Zhu, Tianyu Wang, and Pheng-Ann Heng
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), vol. 31, no. 3, pp. 1079-1090, 2021.
    [paper] [arXiv] [supp.] [code] [results]

  • Rotation-oriented Collaborative Self-supervised Learning for Retinal Disease Diagnosis
    Xiaomeng Li, Xiaowei Hu, Xiaojuan Qi, Lequan Yu, Wei Zhao, Pheng-Ann Heng, and Lei Xing
    IEEE Transactions on Medical Imaging (IEEE TMI), vol. 40, no. 9, pp. 2284-2294, 2021. (TMI Popular Paper)
    [paper] [code]

  • SALMNet: A Structure-Aware Lane Marking Detection Network
    Xuemiao Xu, Tianfei Yu, Xiaowei Hu*, Wing W. Y. Ng*, and Pheng-Ann Heng
    IEEE Transactions on Intelligent Transportation Systems (IEEE TITS), vol. 22, no. 8, pp. 4986-4997, 2021.
    [paper]

  • Learning Gated Non-Local Residual for Single-Image Rain Streak Removal
    Lei Zhu, Zijun Deng, Xiaowei Hu*, Haoran Xie, Xuemiao Xu*, Jing Qin, and Pheng-Ann Heng
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), vol. 31, no. 6, pp. 2147-2159, 2021.
    [paper]

  • Learning Semantic Context from Normal Samples for Unsupervised Anomaly Detection
    Xudong Yan, Huaidong Zhang, Xuemiao Xu, Xiaowei Hu, and Pheng-Ann Heng
    AAAI Conference on Artificial Intelligence (AAAI), vol. 35, no. 4, pp. 3110-3118, 2021.
    [paper] [code]

  • Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images
    Cheng Xue, Lei Zhu, Huazhu Fu, Xiaowei Hu, Xiaomeng Li, Hai Zhang, and Pheng-Ann Heng
    Medical Image Analysis (MedIA), vol. 70, article no. 101989, 2021.
    [paper] [arXiv]

2020

  • Direction-Aware Spatial Context Features for Shadow Detection and Removal
    Xiaowei Hu, Chi-Wing Fu, Lei Zhu, Jing Qin, and Pheng-Ann Heng
    IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), vol. 42, no. 11, pp. 2795-2808, 2020.
    [paper] [arXiv] [supp.] [code]

  • Instance Shadow Detection
    Tianyu Wang^, Xiaowei Hu^, Qiong Wang, Pheng-Ann Heng, and Chi-Wing Fu
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1880-1889, 2020.
    [paper] [arXiv] [code] [SOBA dataset] [results] [video]

  • Saliency-Aware Texture Smoothing
    Lei Zhu^, Xiaowei Hu^, Chi-Wing Fu, Jing Qin, and Pheng-Ann Heng
    IEEE Transactions on Visualization and Computer Graphics (IEEE TVCG), vol. 26, no. 7, pp. 2471-2484, 2020.
    [paper] [code] [SDTS dataset]

  • Ψ-Net: Stacking Densely Convolutional LSTMs for Sub-cortical Brain Structure Segmentation
    Lihao Liu^, Xiaowei Hu^, Lei Zhu, Chi-Wing Fu, Jing Qin, and Pheng-Ann Heng
    IEEE Transactions on Medical Imaging (IEEE TMI), vol. 39, no. 9, pp. 2806-2817, 2020.
    [paper] [code]

  • CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading
    Xiaomeng Li*, Xiaowei Hu*, Lequan Yu, Lei Zhu, Chi-Wing Fu, and Pheng-Ann Heng
    IEEE Transactions on Medical Imaging (IEEE TMI), vol. 39, no. 5, pp. 1483-1493, 2020. (ESI Highly Cited Paper)
    [paper] [code]

  • GrabAR: Occlusion-aware Grabbing Virtual Objects in AR
    Xiao Tang, Xiaowei Hu, Chi-Wing Fu, and Daniel Cohen-Or
    ACM Symposium on User Interface Software and Technology (UIST), pp. 697-708, 2020.
    [paper] [arXiv] [project]

  • Aggregating Attentional Dilated Features for Salient Object Detection
    Lei Zhu, Jiaxing Chen, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Jing Qin, and Pheng-Ann Heng
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), vol. 30, no. 10, pp. 3358-3371, 2020.
    [paper] [code] [results]

2019

  • Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data
    Xiaowei Hu, Yitong Jiang, Chi-Wing Fu, and Pheng-Ann Heng
    IEEE International Conference on Computer Vision (ICCV), pp. 2472-2481, 2019.
    [paper] [arXiv] [code] [USR dataset] [poster]

  • Deep Multi-Model Fusion for Single-Image Dehazing
    Zijun Deng, Lei Zhu, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Qing Zhang, Jing Qin, and Pheng-Ann Heng
    IEEE International Conference on Computer Vision (ICCV), pp. 2453-2462, 2019.
    [paper] [code] [results]

  • Depth-Attentional Features for Single-Image Rain Removal
    Xiaowei Hu, Chi-Wing Fu, Lei Zhu, and Pheng-Ann Heng
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8022-8031, 2019.
    [paper] [supp.] [code] [RainCityscapes dataset] [poster]

  • SINet: A Scale-Insensitive Convolutional Neural Network for Fast Vehicle Detection
    Xiaowei Hu, Xuemiao Xu, Yongjie Xiao, Hao Chen, Shengfeng He, Jing Qin, and Pheng-Ann Heng
    IEEE Transactions on Intelligent Transportation Systems (IEEE TITS), vol. 20, no. 3, pp. 1010-1019, 2019. (ESI Highly Cited Paper)
    [paper] [arXiv] [code] [LSVH dataset (Google)] [LSVH dataset (Baidu)]

  • Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration
    Lihao Liu, Xiaowei Hu, Lei Zhu, and Pheng-Ann Heng
    International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 346-354, 2019.
    [paper] [arXiv] [code]

  • Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound
    Yi Wang, Haoran Dou, Xiaowei Hu, Lei Zhu, Xin Yang, Ming Xu, Jing Qin, Pheng-Ann Heng, Tianfu Wang, and Dong Ni
    IEEE Transactions on Medical Imaging (IEEE TMI), vol. 38, no. 12, pp. 2768-2778, 2019.
    [paper] [arXiv] [code]

  • Enhancing Augmented VR Interaction via Egocentric Scene Analysis
    Yang Tian, Chi-Wing Fu, Shengdong Zhao, Ruihui Li, Xiao Tang, Xiaowei Hu, and Pheng-Ann Heng
    Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (Ubicomp), vol. 3, no. 3, article no. 105, 2019.
    [paper]

  • CATARACTS: Challenge on Automatic Tool Annotation for cataRACT Surgery
    Hassan Al Hajj, Mathieu Lamard, Pierre-Henri Conze, Soumali Roychowdhury, Xiaowei Hu, et al.
    Medical Image Analysis (MedIA), vol. 52, pp. 24-41, 2019.
    [paper]

2018 & Before

  • Direction-Aware Spatial Context Features for Shadow Detection
    Xiaowei Hu, Lei Zhu, Chi-Wing Fu, Jing Qin, and Pheng-Ann Heng
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7454-7462, 2018. (Oral)
    [paper] [arXiv] [supp.] [code] [results] [poster] [slides] [video]

  • Recurrently Aggregating Deep Features for Salient Object Detection
    Xiaowei Hu, Lei Zhu, Jing Qin, Chi-Wing Fu, and Pheng-Ann Heng
    AAAI Conference on Artificial Intelligence (AAAI), pp. 6943-6950, 2018. (Spotlight)
    [paper] [supp.] [code] [results] [poster]

  • R³Net: Recurrent Residual Refinement Network for Saliency Detection
    Zijun Deng^, Xiaowei Hu^, Lei Zhu, Xuemiao Xu, Jing Qin, Guoqiang Han, and Pheng-Ann Heng
    International Joint Conference on Artificial Intelligence (IJCAI), pp. 684-690, 2018. (Oral)
    [paper] [code] [results] [poster] [slides]

  • Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection
    Lei Zhu, Zijun Deng, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Jing Qin, and Pheng-Ann Heng
    European Conference on Computer Vision (ECCV), pp. 122-137, 2018.
    [paper] [code] [poster]

  • Deep Attentional Features for Prostate Segmentation in Ultrasound
    Yi Wang, Zijun Deng, Xiaowei Hu, Lei Zhu, Xin Yang, Xuemiao Xu, Pheng-Ann Heng, and Dong Ni
    International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 523-530, 2018.
    [paper] [code]

  • AGNet: Attention-Guided Network for Surgical Tool Presence Detection
    Xiaowei Hu, Lequan Yu, Hao Chen, Jing Qin, and Pheng-Ann Heng
    Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp. 186-194, 2017.
    [paper] [code]

PhD Thesis

  • Shadow Detection and Removal with Deep Learning
    Xiaowei Hu
    The Chinese University of Hong Kong, June, 2020.
    [thesis]

Patents