My research interests include Graph Signal Processing (GSP), Graph Neural Network (GNN), as well as the intersection between GSP and GNN for interpretable graph-based machine learning, as described below. Please refer to our overview paper on "Graph Signal Processing for Geometric Data and Beyond: Theory and Applications" [arXiv] for more discussions.

We apply the proposed GSP/GNN paradigms to the processing, analysis and synthesis of geometric data, images, brain signals, etc., with the current focus on geometric data such as 3D point clouds. Below are some major problems we address.

1. Point cloud restoration

Point cloud restoration is an inverse problem to reconstruct point clouds from degraded versions, including denoising, inpainting, upsampling, etc.. As graphs provide structure-adaptive, accurate, and compact representations for geometric data, we focus on point cloud restoration via graph signal processing and graph-based machine learning.

Point cloud denoising	Point cloud upsampling

 

Selected Relevant Papers:

• Haolan Chen, Bi'an Du, Shitong Luo, Wei Hu, "Deep Point Set Resampling via Gradient Fields," accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), May 2022.
• Wei Hu, Xiang Gao, Gene Cheung, Zongming Guo, "Feature Graph Learning for 3D Point Cloud Denoising," IEEE Transactions on Signal Processing (TSP), vol. 68, pp. 2841-2856, February 2020.
• Wei Hu, Qianjiang Hu, Zehua Wang, Xiang Gao, "Dynamic Point Cloud Denoising via Manifold-to-Manifold Distance," IEEE Transactions on Image Processing (TIP), vol. 30, pp. 6168-6183, July, 2021.
• Shitong Luo, Wei Hu, "Score-Based Point Cloud Denoising," International Conference on Computer Vision (ICCV), 2021.

 

2. Point cloud classification / segmentation

We focus on self-supervised/weakly-supervised/robust graph representation learning for point cloud classification and segmentation.

Point cloud classification (ModelNet)	Point cloud segmentation (ShapeNet)

 

Selected Relevant Papers:

• Xiang Gao, Wei Hu, Guo-Jun Qi, "GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, June 2020.
• Xiang Gao, Wei Hu, Guo-Jun Qi, "Self-Supervised Graph Representation Learning via Topology Transformations," accepted to IEEE Transactions on Knowledge and Data Engineering (TKDE), December, 2021. 
• Daizong Liu, Wei Hu, "Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification," accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), July 2022. 
• Gusi Te, Wei Hu, Amin Zheng, Zongming Guo, "RGCNN: Regularized Graph CNN for Point Cloud Segmentation," ACM International Conference on Multimedia (ACM MM), Seoul, Republic of Korea, October 2018.

 

3. Point cloud generation

Learning generative models for point clouds is powerful in unsupervised representation learning to characterize the data distribution, which lays the foundation for various tasks such as shape completion, upsampling, synthesis, etc.

 

Selected Relevant papers:

• Shitong Luo, Wei Hu, "Diffusion Probabilistic Models for 3D Point Cloud Generation," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2021. [Best Paper Candidate, 1 of 32 chosen from 7015 submissions]

 

4. Point cloud compression

The large amount of data in 3D point clouds significantly increase the burden for transmission and storage, especially with multiple attributes on each point. Hence, it is quite challenging to represent point clouds compactly, and efficient point cloud compression is required.

 

Selected Relevant papers:

• Yiqun Xu, Wei Hu, Shanshe Wang, Xinfeng Zhang, Shiqi Wang, Siwei Ma, Zongming Guo, Wen Gao, "Predictive Generalized Graph Fourier Transform for Attribute Compression of Dynamic Point Clouds," IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 31, no. 5, pp. 1968-1982, May 2021.

 

Current Ph.D. / Master Students

Daizong Liu	Zehua Wang	Qianjiang Hu	Haolan Chen
Bi'an Du	Zhimin Zhang	Pufan Li	Wencan Huang
Junyi Yao	Tianshu Shen

Co-supervised Ph.D. Student

Yang Liu

Alumni

Xiang Gao	Gusi Te

 

#: corresponding author, *: co-first author

Book Chapter

• Wei Hu, Siheng Chen, Dong Tian [link]
  Graph Spectral Point Cloud Processing
  Graph Spectral Image Processing, ISTE/Wiley, June 2021.

 

Submitted Journal Papers​

• Daizong Liu, Mingyu Yang, Xiaoye Qu, Pan Zhou, Yu Cheng, Wei Hu^#
  A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends [arXiv]
  submitted to IEEE Transactions on Knowledge and Data Engineering (TKDE), August, 2024.
• Daizong Liu, Yunbo Tao, Pan Zhou, Wei Hu^#
  Hard-Label Black-Box Attacks on 3D Point Clouds
  submitted to  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), May, 2024.
• Daizong Liu, Yang Liu, Wencan Huang, Wei Hu^#
  A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions [arXiv]
  submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), July, 2024.
• Xiang Gao, Wei Hu^#, Renjie Liao
  Learning Latent Part-Whole Hierarchies for Point Clouds [arXiv]
  submitted to International Journal of Computer Vision (IJCV), September, 2023

 

Paper Publications

2025

• Shiyu Hu, Daizong Liu, Wei Hu
  Improving the Transferability of 3D Point Cloud Attack via Spectral-aware Admix and Optimization Designs
  in The 34th International Conference on Artificial Neural Networks (ICANN), 2025


• Jingchen Zhu, Chenhao Xue,  Yiqi Chen, Zhao Wang, Chen Zhang, Yu Shen, Yifan Chen, Zekang Cheng, Yu Jiang, Tianqi Wang, Yibo Lin, Wei Hu, BinCui, Runsheng Wang, Yun Liang, Guangyu Sun
  Theseus: Exploring Efficient Wafer-Scale Chip Design for Large Language Models
  in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), May, 2025


• Gabriele Spadaro, Alberto Presta, Jhony H. Giraldo, Marco Grangetto, Wei Hu, Giuseppe Valenzise, Attilio Fiandrotti, Enzo Tartaglione
  Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates
  in IEEE International Conference on Multimedia & Expo (ICME), 2025


• Daizong Liu,  Wei Hu^#
  Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks
  in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025


• Qianjiang Hu, Wei Hu^#
  Dynamic Point Cloud Denoising via Gradient Fields 
  accepted to Transactions on Multimedia Computing Communications and Applications (TOMM), February, 2025.


• Zehua Wang, Yang Liu, Wei Hu^#
  Molecular Representation Learning via Hierarchical Graph Transformer [PDF]
  accepted to APSIPA Transactions on Signal and Information Processing, January, 2025.

2024

• Daizong Liu, Wei Hu^#
  Imperceptible Backdoor Attacks on Text-Guided 3D Scene Grounding. 
  accepted to IEEE Transactions on Multimedia (TMM), July, 2024.


• Yang Liu, Daizong Liu, Wei Hu^#
  Joint Top-Down and Bottom-Up Frameworks for 3D Visual Grounding.
  accepted to International Conference on Pattern Recognition (ICPR), 2024


• Yang Liu, Daizong Liu, Zongming Guo, Wei Hu^#
  Cross-Task Knowledge Transfer for Semi-supervised Joint 3D Grounding and Captioning [PDF]
  accepted to ACM International Conference on Multimedia (ACM MM), 2024


• Wencan Huang, Daizong Liu, Wei Hu^#
  Advancing 3D Object Grounding Beyond a Single 3D Scene [PDF]
  accepted to ACM International Conference on Multimedia (ACM MM), 2024


• Qianjiang Hu, Zhimin Zhang, Wei Hu^#
  RangeLDM: Fast Realistic LiDAR Point Cloud Generation [PDF]
  accepted to European Conference on Computer Vision (ECCV), September, 2024. 


• Zichen Wang, Jing Yu, Muyue Zhai, Zehua Wang, Kaiwen Sheng, Yu Zhu, Tianyu Wang, Mianzhi Liu, Lu Wang, Miao Yan, Jue Zhang, Ying Xu, Xianhua Wang, Lei Ma^#, Wei Hu^#, Heping Cheng^#
  System-level time computation and representation in the suprachiasmatic nucleus revealed by large-scale calcium imaging and machine learning [PDF]
  accepted to Cell Research, March, 2024.


• Bi'an Du, Xiang Gao, Wei Hu^#, Renjie Liao
  Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing [PDF]
  accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR), March, 2024.

 

2023

• Daizong Liu, Wei Hu^# 
  Explicitly Perceiving and Preserving the Local Geometric Structures for 3D Point Cloud Attack [PDF]
  accepted to the 38th AAAI Conference on Artificial Intelligence (AAAI), December, 2023.


• Jincen Jiang, Lizhi Zhao, Xuequan Lu, Wei Hu, Imran Razzak, Meili Wang 
  DHGCN: Dynamic Hop Graph Convolution Network for Self-supervised Point Cloud Learning [PDF]
  accepted to the 38th AAAI Conference on Artificial Intelligence (AAAI), December, 2023.


• Zhimin Zhang, Xiang Gao, Wei Hu^# 
  InvariantOODG: Learning Invariant Features of Point Clouds for Out-of-Distribution Generalization [PDF]
  accepted to International Conference on Acoustics, Speech, and Signal Processing (ICASSP), December, 2023.


• Daizong Liu, Wei Hu^#, Xin Li 
  Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing [arXiv]
  accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), November, 2023.


• Ruiguo Yang, Xinhui Han, Wenfa Qi and Wei Hu
  Robust Watermark Imaging via Graph-Signal Optimization [PDF]
  Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Taipei, Taiwan, October, 2023.


• Daizong Liu, Wei Hu^#, Xin Li 
  Robust Geometry-Dependent Attack for 3D Point Clouds [PDF]
  accepted to IEEE Transactions on Multimedia (TMM), August, 2023.


• Wencan Huang, Daizong Liu, Wei Hu^#
  Dense Object Grounding in 3D Scenes [PDF]
  accepted to ACM International Conference on Multimedia (ACM MM), 2023


• Yunbo Tao, Daizong Liu, Pan Zhou, Yulai Xie, Wei Du, Wei Hu^#
  3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack [PDF]
  accepted to International Conference on Computer Vision (ICCV), 2023.


• Pufan Li, Xiang Gao, Qianjiang Hu, Wei Hu^#
  Robust Graph-based Segmentation of Noisy Point Clouds [PDF]
  accepted to IEEE International Conference on Image Processing (ICIP), 2023.


• Xiang Gao, Wei Hu^#, Guo-Jun Qi
  Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations [PDF]
  accepted to ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP), May, 2023.


• Qianjiang Hu, Daizong Liu, Wei Hu^#
  Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection [PDF]
  accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR), March, 2023.


• Daizong Liu, Xiang Fang, Wei Hu^#, Pan Zhou^#
  Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding [arXiv]
  accepted to IEEE Transactions on Multimedia (TMM), January, 2023.


• Jin Zeng, Yang Liu, Gene Cheung, Wei Hu^#
  Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks [PDF]
  accepted to International Conference on Acoustics, Speech, and Signal Processing (ICASSP), January, 2023.

 

2022

• Daizong Liu, Wei Hu^#
  Rethinking Graph Neural Networks for Unsupervised Video Object Segmentation [PDF]
  accepted to British Machine Vision Conference (BMVC), 2022


• Daizong Liu, Wei Hu^#
  Learning to Focus on the Foreground for Temporal Sentence Grounding [PDF]
  accepted to International Conference on Computational Linguistics (COLING), 2022


• Daizong Liu, Wei Hu^#
  Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification [arXiv]
  accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), July, 2022.


• Qianjiang Hu^*, Daizong Liu^*, Wei Hu^#
  Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks​ [arXiv][Code]
  accepted to European Conference on Computer Vision (ECCV), July 2022.


• Gusi Te, Xiu Li, Xiao Li, Jinglu Wang, Wei Hu^#, Yan Lu^#
  Neural Capture of Animatable 3D Human from Monocular Video​ [arXiv]
  accepted to European Conference on Computer Vision (ECCV), July 2022.


• Daizong Liu, Wei Hu^#
  Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization [arXiv]
  accepted to ACM International Conference on Multimedia (ACM MM), June, 2022. 


• Daizong Liu, Xiaoye Qu, Wei Hu^#
  Reducing the Vision and Language Bias for Temporal Sentence Grounding [Oral]
  accepted to ACM International Conference on Multimedia (ACM MM), June, 2022.


• Haolan Chen*, Bi'an Du*, Shitong Luo, Wei Hu^#
  Deep Point Set Resampling via Gradient Fields [arXiv][Code]
  accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), April, 2022.

 

2021

• Xiang Gao, Wei Hu^#, Guo-Jun Qi
  Self-Supervised Graph Representation Learning via Topology Transformations [arXiv] [Code]
  accepted to IEEE Transactions on Knowledge and Data Engineering (TKDE), December, 2021.


• Wenfa Qi, Sirui Guo, Wei Hu^#
  Generic Reversible Visible Watermarking Via Regularized Graph Fourier Transform Coding [arXiv]
  accepted to IEEE Transactions on Image Processing (TIP), November, 2021.


• Wei Hu, Jiahao Pang, Xianming Liu, Dong Tian, Chia-Wen Lin^#, Anthony Vetro
  Graph Signal Processing for Geometric Data and Beyond: Theory and Applications [arXiv]
  accepted to IEEE Transactions on Multimedia (TMM), September, 2021.


• Gusi Te, Wei Hu^#, Yinglu Liu, Hailin Shi, Tao Mei
  Adaptive Graph Representation Learning and Reasoning for Face Parsing [arXiv]
  accepted to IEEE Transactions on Image Processing (TIP), August, 2021.


• Haolan Chen, Shitong Luo, Xiang Gao, Wei Hu^#
  Unsupervised Learning of Geometric Sampling Invariant Representations for 3D Point Clouds [PDF]
  accepted to IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021.


• Shitong Luo, Wei Hu^#
  Score-Based Point Cloud Denoising [PDF]
  International Conference on Computer Vision (ICCV), 2021.


• Bi'an Du^*, Xiang Gao^*, Wei Hu^#, Xin Li
  Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning [PDF]
  accepted to ACM International Conference on Multimedia (ACM MM), July, 2021.


• Cheng Yang, Gene Cheung^#, Wei Hu^#
  Signed Graph Metric Learning via Gershgorin Disc Alignment [arXiv] [Code]
  accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), June, 2021.


• Wei Hu^#, Qianjiang Hu, Zehua Wang, Xiang Gao
  Dynamic Point Cloud Denoising via Manifold-to-Manifold Distance [arXiv]
  accepted to IEEE Transactions on Image Processing (TIP), June, 2021.


• Yiming He, Wei Hu^#
  3D Hand Pose Estimation via Regularized Graph Representation Learning [PDF] [Best Poster Award]
  accepted to The CAAI International Conference on Artificial Intelligence (CICAI), May, 2021.


• Qianjiang Hu, Xiao Wang, Wei Hu^#, Guo-Jun Qi^#
  AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries [PDF] [Code]
  accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR), March, 2021.


• Shitong Luo, Wei Hu^#
  Diffusion Probabilistic Models for 3D Point Cloud Generation [PDF] [Code] [Best Paper Candidate, 32 out of 7015 submissions]
  accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR), March, 2021.


• Jiaxiang Tang, Xiang Gao, Wei Hu^#
  RGLN: Robust Residual Graph Learning Networks via Similarity-Preserving Mapping on Graphs [PDF]
  accepted to International Conference on Acoustics, Speech, and Signal Processing (ICASSP), January, 2021.

 

2020

• Zeqing Fu, Wei Hu^#
  Dynamic Point Cloud Inpainting via Spatial-Temporal Graph Learning [PDF] [Invited to the Best Paper Track of TMM]
  accepted to IEEE Transactions on Multimedia (TMM), 2020.


• Wenquan Xu, Haoyu Song, LinYang Hou, Hui Zheng, Xinggong Zhang, Chuwen Zhang, Wei Hu, Yi Wang, Bin Liu^#
  SODA: Similar 3D Object Detection Accelerator at Network Edge for Autonomous Driving
  accepted to INFOCOM, 2020.


• Yiqun Xu, Wei Hu^#, Shanshe Wang, Xinfeng Zhang, Shiqi Wang, Siwei Ma^#, Zongming Guo, Wen Gao
  Predictive Generalized Graph Fourier Transform for Attribute Compression of Dynamic Point Clouds [PDF]
  accepted to IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Aug. 2020.


• Shitong Luo, Wei Hu^#
  Differentiable Manifold Reconstruction for Point Cloud Denoising [PDF] [Code] [Oral, acceptance rate: 8.89%]
  accepted to ACM International Conference on Multimedia (ACM MM), Seattle, United States, October 2020.


• Gusi Te, Yinglu Liu, Wei Hu^#, Hailin Shi, Tao Mei
  Edge-aware Graph Representation Learning and Reasoning for Face Parsing [PDF] [Code]
  European Conference on Computer Vision (ECCV), August 2020.


• Jie Li, Cong Zhang, Zhi Liu, Wei Sun, Wei Hu, Qiyue Li
  Narwhal: a DASH-based Point Cloud Video Streaming System over Wireless Networks [PDF]
  IEEE INFOCOM demo, July, Toronto, Canada.


• Xiang Gao, Wei Hu^#, Zongming Guo
  Exploring Structure-Adaptive Graph Learning for Robust Semi-Supervised Classification [PDF] [Oral]
  IEEE International Conference on Multimedia and Expo (ICME), London, July 2020.


• Zeqing Fu, Wei Hu^#, Zongming Guo
  3D Dynamic Point Cloud Inpainting Via Temporal Consistency on Graphs [PDF] [Best Student Paper Runner Up Award, 5/834 submissions]
  IEEE International Conference on Multimedia and Expo (ICME), London, July 2020.


• Gusi Te, Wei Hu^#, Zongming Guo
  Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks [PDF]
  IEEE International Conference on Multimedia and Expo (ICME), London, July 2020.


• Xiang Gao, Wei Hu^#, Guo-Jun Qi
  GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations [PDF] [Code]
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, June 2020.


• Wei Hu^*#, Xiang Gao^*, Gene Cheung, Zongming Guo
  Feature Graph Learning for 3D Point Cloud Denoising [PDF] [Code]
  IEEE Transactions on Signal Processing (TSP), May, 2020.


• Cheng Yang, Gene Cheung, Wei Hu
  Fast Graph Metric Learning via Gershgorin Disc Alignment [PDF]
  International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, May 2020.

 

2019

• Xiang Gao, Wei Hu^#, Jiaxiang Tang, Jiaying Liu, Zongming Guo
  Optimized Skeleton-based Action Recognition via Sparsified Graph Regression [PDF]
  ACM International Conference on Multimedia (ACM MM), Nice, France, Oct. 21-25, 2019.


• Ziling Huang, Zheng Wang^#, Wei Hu^#, Chia-Wen Lin, Shin'Ichi Satoh
  DoT-GNN: Domain-Transferred Graph Neural Network for Group Re-identification [PDF]
  ACM International Conference on Multimedia (ACM MM), Nice, France, Oct. 21-25, 2019.


• Ju He, Zeqing Fu, Wei Hu^#, Zongming Guo
  Point Cloud Attribute Inpainting in Graph Spectral Domain [PDF] [Oral]
  IEEE International Conference on Image Processing (ICIP), Taiwan, Sept. 22-25, 2019.


• Wei Hu^*#, Zeqing Fu^*#, Zongming Guo
  Local Frequency Interpretation and Non-Local Self-Similarity on Graph for Point Cloud Inpainting [PDF]
  IEEE Transactions on Image Processing (TIP), vol. 28, no. 8, pp. 4087-4100, Aug. 2019


• Junkun Qi, Wei Hu^#, Zongming Guo
  Feature Preserving and Uniformity-Controllable Point Cloud Simplification on Graph [PDF] [Code] [Oral]
  IEEE International Conference on Multimedia and Expo (ICME), Shanghai, Jul. 8-12, 2019.

 

2018

• Gusi Te, Wei Hu^#, Amin Zheng, Zongming Guo
  RGCNN: Regularized Graph CNN for Point Cloud Segmentation [PDF] [Code]
  ACM International Conference on Multimedia (ACM MM), Seoul, Republic of Korea, Oct. 22-26, 2018.


• Xiang Gao, Wei Hu^#, Zongming Guo
  Graph-based Point Cloud Denoising [PDF]
  IEEE International Conference on Multimedia Big Data (BigMM), Xi'an, China, Sept. 13-16, 2018.


• Weihang Liao, Gene Cheung, Wei Hu
  Path Coding on Geometric Planar Graph for 2D/3D Visual Data Partitioning [PDF]
  IEEE International Conference on Image Processing (ICIP), Athens, Greece, Oct. 7-10, 2018.


• Zeqing Fu, Wei Hu^#, Zongming Guo
  Point Cloud Inpainting on Graphs from Non-local Self-similarity [PDF]
  IEEE International Conference on Image Processing (ICIP), Athens, Greece, Oct. 7-10, 2018.


• Wei Hu, Mozhdeh Seifi, Erik Reinhard
  Over- and Under-Exposure Reconstruction of a Single Plenoptic Capture [PDF]
  ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), vol. 14, no. 2, p. 52, May, 2018.


• Yiqun Xu, Wei Hu^#, Shanshe Wang^#, Xinfeng Zhang, Shiqi Wang, Siwei Ma^#, Wen Gao^#
  Cluster-Based Point Cloud Coding With Normal Weighted Graph Fourier Transform [PDF]
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Alberta, Canada, Apr. 15-20, 2018

 

Before 2017

• Wei Hu, Mozhdeh Seifi, Erik Reinhard
  Optical Center Estimation for Lenslet-based Plenoptic Cameras [PDF]
  IEEE International Workshop on Multimedia Signal Processing, Luton, Oct. 16-18, 2017.


• Wei Hu, Gene Cheung, Masato Kazui
  Graph-based Dequantization of Block-Compressed Piecewise Smooth Images [PDF]
  IEEE Signal Processing Letters, vol. 23, no. 2, pp. 242-246, February, 2016. (Patent filed with Samsung Japan.)


• Wei Hu, Gene Cheung, Antonio Ortega
  Intra-Prediction and Generalized Graph Fourier Transform for Image Coding [PDF] [Code]
  IEEE Signal Processing Letters, vol. 22, no. 11, pp. 1913-1917, November, 2015.


• Yung-Hsuan Chao, Antonio Ortega, Wei Hu, Gene Cheung
  Edge-Adaptive Depth Map Coding with Lifting Transform on Graphs [PDF]
  31st Picture Coding Symposium, Cairns, Australia, May 31 - Jun. 3, 2015.


• Wei Hu, Gene Cheung, Antonio Ortega, Oscar C. Au
  Multi-resolution Graph Fourier Transform for Compression of Piecewise Smooth Images [PDF] [Code]
  IEEE Transactions on Image Processing (TIP), vol. 24, no. 1, pp. 419-433, January, 2015.


• Jiahao Pang, Gene Cheung, Wei Hu, Oscar C. Au
  Redefining Self-Similarity in Natural Images for Denoising Using Graph Signal Gradient [PDF]
  Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Siem Reap, city of Angkor Wat, Cambodia, Dec. 9-12, 2014.


• Rui Ma, Oscar C. Au, Pengfei Wan, Lingfeng Xu, Wenxiu Sun, Wei Hu
  Improved Temporal Psychovisual Modulation for Backward-Compatible Stereoscopic Display [PDF]
  IEEE Global Conference on Signal and Information Processing (GlobalSIP), Atlanta, Georgia, USA, Dec. 3-5, 2014.


• Wei Hu, Gene Cheung, Xin Li, Oscar C. Au
  Graph-based Joint Denoising and Super-resolution of Generalized Piecewise Smooth Images [PDF] [Top 10% paper award]
  International Conference on Image Processing (ICIP), Paris, France, Oct. 27-30, 2014. (Top 10% paper award.)


• Wei Dai, Oscar C. Au, Wenjing Zhu, Pengfei Wan, Wei Hu, Jiantao Zhou
  SSIM-based rate-distortion optimization in H.264 [PDF]
  IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Florence, Italy, May 4-9, 2014.


• Wenxiu Sun, Oscar C. Au, Lingfeng Xu, Yujun Li, Wei Hu
  Seamless View Synthesis through Texture Optimization [PDF]
  IEEE Transactions on Image Processing (TIP), vol. 23, no. 1, pp. 342-355, January, 2014.


• Wei Hu, Xin Li, Gene Cheung, Oscar C. Au
  Depth Map Denoising using Graph-based Transform and Group Sparsity [PDF] [Code] [Top 10% paper award]
  IEEE International Workshop on Multimedia Signal Processing, Pula, Italy, Sept. 30 - Oct. 2, 2013. (Top 10% paper award.)


• Wei Dai, Oscar C. Au, Wenjing Zhu, Wei Hu, Pengfei Wan, Jiali Li
  A robust interpolation-free approach for sub-pixel accuracy motion estimation [PDF]
  IEEE International Conference on Image Processing (ICIP), Melbourne, Australia, Sept. 15-18, 2013.


• Chao Pang, Oscar C. Au, Feng Zou, Xingyu Zhang, Wei Hu, Pengfei Wan
  Optimal dependent bit allocation for AVS intra-frame coding via successive convex approximation [PDF]
  IEEE International Conference on Image Processing (ICIP), Melbourne, Australia, Sept. 15-18, 2013.


• Ruobing Zou, Oscar C. Au, Guyue Zhou, Wei Dai, Wei Hu, Pengfei Wan
  Personal photo album compression and management [PDF]
  IEEE International Symposium on Circuits and Systems (ISCAS), Beijing, China, May 19-23, 2013.


• Lingfeng Xu, Oscar C. Au, Wenxiu Sun, Jiali Li, Wei Hu, Rui Ma
  Ray-Space based Camera Spacing Correction via Convex Optimization [PDF]
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, Canada, May 26-31, 2013.


• Wenxiu Sun, Oscar C. Au, Lingfeng Xu, Yujun Li, Wei Hu, Zhiding Yu
  Texture Optimization for Seamless View Synthesis Through Energy Minimization [PDF]
  ACM International Conference on Multimedia (ACM MM), Nara, Japan, Oct. 29 - Nov. 2, 2012.


• Wei Hu, Gene Cheung, Xin Li, Oscar C. Au
  Depth Map Compression using Multi-resolution Graph-based Transform for Depth-image-based Rendering [PDF]
  IEEE International Conference on Image Processing (ICIP), Orland, Florida, U.S.A, Sept. 30 - Oct. 3, 2012. (Patent filed.)


• Yujun Li, Oscar C. Au, Lingfeng Xu, Wenxiu Sun, Wei Hu
  Inferring Depth from a Pair of Images Captured Using Different Aperture Settings [PDF]
  International Conference on Multimedia Modeling, China, September, 2012.


• Wei Hu, Gene Cheung, Xin Li, Oscar C. Au
  Depth Map Super-resolution Using Synthesized View Matching for Depth-image-based Rendering [PDF]
  3rd International Workshop on Hot Topics in 3D (in conjunction with ICME 2012), Melbourne, Australia, July, 2012.


• Wei Hu, Oscar C. Au, Lin Sun, Wenxiu Sun, Lingfeng Xu, Yujun Li
  Adaptive Depth Map Filter for Blocking Artifacts Removal and Edge Preserving [PDF]
  IEEE International Symposium on Circuits and Systems (ISCAS), Seoul, Korea, May 20-23, 2012.

 

Funded Research Projects

1. 国家重点研发计划，2021YFF0901500，全媒体内容智能生产技术与平台，2021/12-2024/11，1432万元/5900万元，在研，课题二负责人


2. 国家自然科学基金面上项目，61972009，基于谱图理论的多分辨率图卷积神经网络研究，2020/01-2023/12，59万元，在研，主持


3. 国家重点研发计划“科技冬奥”重点专项，2019YFF0302900，冰雪项目交互式多维度观赛体验技术与系统-VR 编码与传输平台，2019/10-2022/06，67/546万元，在研，课题骨干（子项目负责人）


4. 国家重点研发计划，2018YFB1003504，基于异构图计算机的数据管理与分析系统，2018/05-2021/04，25/650万元，在研，课题骨干


5. 北京市自然科学基金青年项目，4194080，基于图谱论的三维点云重建研究，2019/01-2020/12，10万元，在研，主持


6. 北京市自然科学基金-海淀原始创新联合基金项目，19L2133，基于三维点云的混合现实个性化骨关节手术模拟重建，2019/12-2022/12，9/28万元，在研，联合主持


7. 北京大学医学交叉研究种子基金，BMU2018MI016，基于影像的个性化虚拟现实模拟临床手术的研究，2019/01-2019/12，10/20万元，已结题，联合主持


8. Alibaba Innovation Research，No. XTG201800108，基于图的3D点云压缩，2018/01-2018/12，41万元，已结题，主持


9. MSRA Collaborative Research, FY18-Research-Sponsorship-029，Graph Neural Networks for 3D Face Anti-spoofing, 2018/01-2018/12，20万元，已结题，主持


10. 北京大学中央高校基本科研业务费专项，7100601213，点云的高效编码，2017/07-2020/12，40万元，在研，主持

 

Patents

Granted Patents

1. 胡玮，傅泽卿，郭宗明
   基于局域平滑性和非局域相似性的三维点云修复方法
   2020-10-16，中国，201811610195.6


2. 胡玮，特古斯
   一种基于边缘信息和注意力机制的人脸信息识别方法
   2020-07-21，中国，202010704678.3


3. Wei Hu, Erik Reinhard, Mozhdeh Seifi
   Method and device for obtaining a HDR image by graph signal processing
   2019-07-30, U.S., No. 10366478


4. Wei Hu, Erik Reinhard, Mozhdeh Seifi
   Method and an electronic device for calibrating a plenoptic camera
   2019-02-19, U.S., No. 10212321


5. Gene Cheung, Wei Hu
   Encoding device and decoding device for contrast image
   2012-06-21, Japan, JP6188005B2


6. Wenxiu, Sun, Oscar. C. Au, Lingfeng Xu, Yujun Li, Wei Hu, Lu Wang
   Apparatus, system, and method for temporal domain hole filling based on background modeling for view synthesis
   2012-06-29, U.S., 9235879

Pending Patents

1. 胡玮，刘旸，刘岱宗，郭宗明
   联合自上而下和自下而上的三维视觉检索方法及系统
   2024-08-20，中国，202410513849.2


2. 胡玮，高翔，郭宗明
   一种三维多视图共变表征学习方法及三维物体识别方法
   2021-05-10，中国，202110006861.0


3. 胡玮，高翔，郭宗明
   一种无监督图拓扑变换共变表征学习的方法和装置
   2021-04-15，中国，202110035423.7


4. 胡玮，杜康晖，郭宗明
   点云配准方法和装置
   2018-12-12，中国，201811508702.5


5. 胡玮，特古斯，郭宗明
   点云的分割方法、装置及计算机存储介质
   2018-08-16，中国，201810935634.4


6. 胡玮，傅泽卿，郭宗明
   基于图信号处理的点云修复方法、装置及终端
   2018-04-08，中国，201810306574.X


7. 胡玮，高翔，郭宗明
   点云噪声的去除方法、去噪系统、计算机设备及存储介质
   2018-02-08，中国，201810128719.1


8. 马思伟，徐轶群，王苫社，李俊儒，胡玮
   一种基于傅里叶图变换的点云帧内编码方法及装置
   2017-12-21，WIPO, PCT/CN2017/117856

 

•  

• Introduction to Computation (A), Teaching Assistant, Fall Semester 2017
• Graph Signal Processing, Graduate Course, Fall Semester 2018
• Graph Neural Networks, Graduate Course, Fall Semester 2019
• Graph Signal Processing, Graduate Course, Fall Semester 2019
• Graph Neural Networks, Graduate Course, Fall Semester 2020
• Graph Signal Processing, Graduate Course, Fall Semester 2020
• Graph Neural Networks, Graduate Course, Fall Semester 2021
• Graph Signal Processing, Graduate Course, Fall Semester 2021
• Data Structure and Algorithms, Spring Semester 2022
• Graph Neural Networks, Graduate Course, Fall Semester 2022
• Graph Signal Processing, Graduate Course, Fall Semester 2022

Associate Editor for the following Journals

• IEEE Signal Processing Magazine
• IEEE Transactions on Signal and Information Processing over Networks
• Frontiers in Signal Processing

Members of the following Technical Committees

• IEEE Multimedia Systems & Applications Technical Committee (MSA-TC) Member
• IEEE Multimedia Signal Processing Technical Committee (MMSP-TC) Member

Chairs for the following Conferences

• Tutorial Co-Chair for International Conference on Visual Communications and Image Processing (VCIP) 2022
• Co-organizer of ICCV 2021 Workshop on "When Graph Signal Processing meets Computer Vision" [link] [PDF]
• Special Session Co-organizer for International Conference on Image Processing (ICIP) 2021 [link]
• Open Source Co-Chair for International Conference on Multimedia and Expo (ICME) 2021
• Area Chair for ACM International Conference on Multimedia (ACM MM) 2020
• Special Session Co-organizer for International Conference on Multimedia and Expo (ICME) 2020 [link]
• Area Chair for International Conference on Multimedia and Expo (ICME) 2020
• Excutive Area Chair for VALSE since 2020
• Publicity Chair for IEEE International Conference on Multimedia Big Data 2020
• Session Chair for International Conference on Multimedia and Expo (ICME) 2019
• Session Chair for IEEE International Conference on Image Processing (ICIP) 2019

Reviewer for the following Journals/Conferences

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
• IEEE Transactions on Image Processing (TIP)
• IEEE Transactions on Signal Processing (TSP)
• IEEE Transactions on Multimedia (TMM)
• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
• IEEE Signal Processing Letters (SPL)
• IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
• ACM International Conference on Multimedia (ACM MM)
• AAAI Conference on Artificial Intelligence (AAAI), PC member
• IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
• IEEE International Conference on Image Processing (ICIP)
• International Conference on Multimedia and Expo (ICME)
• International Workshop on Multimedia Signal Processing (MMSP)