Publications | Wei Liu

2026

AAAI

AdaDepth: Exploiting Inherent Scene Information for Self-Supervised Depth Estimation in Dynamic Scenes

X. Gao, X. Wu, Z. Ning, R. Yang, Z. Zheng, J. Yang, and W. Liu

In AAAI Conference on Artificial Intelligence (AAAI), 2026

@inproceedings{gao2026adadepth,
  title = {AdaDepth: Exploiting Inherent Scene Information for Self-Supervised Depth Estimation in Dynamic Scenes},
  author = {Gao, X. and Wu, X. and Ning, Z. and Yang, R. and Zheng, Z. and Yang, J. and Liu, W.},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
}

2025

Inter-Modality Feature Representation Learning-based Fusion Network for 3D Industrial Defect Detection

M. Asada, W. Azeemb, A. Alic, Y. Fang, J. Yang, Y. Zuo, and W. Liu

Neural Networks (NN), 2025

Bib

@article{asada2025intermodality,
  title = {Inter-Modality Feature Representation Learning-based Fusion Network for 3D Industrial Defect Detection},
  author = {Asada, M. and Azeemb, W. and Alic, A. and Fang, Y. and Yang, J. and Zuo, Y. and Liu, W.},
  journal = {Neural Networks (NN)},
  year = {2025}
}

TIP

SRS: Siamese Reconstruction-Segmentation Network based on Dynamic-Parameter Convolution

B. Nian, F. Tang, J. Ding, J. Yang, Z. Zheng, S. K. Zhou, and W. Liu

IEEE Transactions on Image Processing (TIP), 2025

Bib

@article{nian2025srs,
  title = {SRS: Siamese Reconstruction-Segmentation Network based on Dynamic-Parameter Convolution},
  author = {Nian, B. and Tang, F. and Ding, J. and Yang, J. and Zheng, Z. and Zhou, S. K. and Liu, W.},
  journal = {IEEE Transactions on Image Processing (TIP)},
  year = {2025}
}

TCSVT

CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Prediction

Z. Ning, Z. Liu, X. Gao, Y. Zuo, J. Yang, Y. Fang, and W. Liu

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025

Bib

@article{ning2025cmf,
  title = {CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Prediction},
  author = {Ning, Z. and Liu, Z. and Gao, X. and Zuo, Y. and Yang, J. and Fang, Y. and Liu, W.},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)},
  year = {2025}
}

ECAI

PMR: Physical Model-Driven Multi-Stage Restoration of Turbulent Dynamic Videos

T. Wu, J. Ye, C. Zhou, W. Chen, Z. Liu, H. Zheng, W. Liu, and Y. Fu

In European Conference on Artificial Intelligence (ECAI), 2025

Bib

@inproceedings{wu2025pmr,
  title = {PMR: Physical Model-Driven Multi-Stage Restoration of Turbulent Dynamic Videos},
  author = {Wu, T. and Ye, J. and Zhou, C. and Chen, W. and Liu, Z. and Zheng, H. and Liu, W. and Fu, Y.},
  booktitle = {European Conference on Artificial Intelligence (ECAI)},
  year = {2025}
}

ACM MM

Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation

F. Tang, B. Nian, J. Ding, W. Ma, Q. Quan, C. Dong, J. Yang, W. Liu, and S. K. Zhou

In Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM), 2025

Bib

@inproceedings{tang2025mobile,
  title = {Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation},
  author = {Tang, F. and Nian, B. and Ding, J. and Ma, W. and Quan, Q. and Dong, C. and Yang, J. and Liu, W. and Zhou, S. K.},
  booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM)},
  year = {2025}
}

ICCV

Fix-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text

B. Wang, Z. Ning, J. Ding, X. Gao, Y. Li, D. Jiang, J. Yang, and W. Liu

In International Conference on Computer Vision (ICCV), 2025

Bib

@inproceedings{wang2025fixclip,
  title = {Fix-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text},
  author = {Wang, B. and Ning, Z. and Ding, J. and Gao, X. and Li, Y. and Jiang, D. and Yang, J. and Liu, W.},
  booktitle = {International Conference on Computer Vision (ICCV)},
  year = {2025},
}

TCSVT

2M3DF: Advancing 3D industrial defect detection with multi perspective multimodal fusion network

M. Asad, W. Azeem, H. Jiang, H. T. Mustafa, J. Yang, and W. Liu

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025

Bib

@article{asad20252m3df,
  title = {2M3DF: Advancing 3D industrial defect detection with multi perspective multimodal fusion network},
  author = {Asad, M. and Azeem, W. and Jiang, H. and Mustafa, H. T. and Yang, J. and Liu, W.},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)},
  year = {2025}
}

TCSVT

Consistency-guided adaptive alternating training for semi-supervised salient object detection

L. Chen, W. Liu, H. Wang, S. W. Jeon, Y. Jiang, and Z. Zheng

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025

Bib

@article{chen2025consistency,
  title = {Consistency-guided adaptive alternating training for semi-supervised salient object detection},
  author = {Chen, L. and Liu, W. and Wang, H. and Jeon, S. W. and Jiang, Y. and Zheng, Z.},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)},
  year = {2025}
}

ICASSP

Mixed Gaussian Splatting for High-Quality Rendering and Reconstruction

S. Liu, J. Ding, J. Yang, and W. Liu

In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025

Bib

@inproceedings{liu2025mixed,
  title = {Mixed Gaussian Splatting for High-Quality Rendering and Reconstruction},
  author = {Liu, S. and Ding, J. and Yang, J. and Liu, W.},
  booktitle = {ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages = {1--5},
  year = {2025},
  organization = {IEEE}
}

MIA

MambaMIM: Pre-training Mamba with state space token interpolation and its application to medical image segmentation

F. Tang, B. Nian, Y. Li, Z. Jiang, J. Yang, W. Liu, and S. K. Zhou

Medical Image Analysis (MIA), 2025

Bib

@article{tang2025mambamim,
  title = {MambaMIM: Pre-training Mamba with state space token interpolation and its application to medical image segmentation},
  author = {Tang, F. and Nian, B. and Li, Y. and Jiang, Z. and Yang, J. and Liu, W. and Zhou, S. K.},
  journal = {Medical Image Analysis (MIA)},
  pages = {103606},
  year = {2025}
}

AEI

3D-MMFN: Multi-level multimodal fusion network for 3D industrial image anomaly detection

M. Asad, W. Azeem, A. A. Malik, H. Jiang, A. Ali, J. Yang, and W. Liu

Advanced Engineering Informatics, 2025

Bib

@article{asad20253dmmfn,
  title = {3D-MMFN: Multi-level multimodal fusion network for 3D industrial image anomaly detection},
  author = {Asad, M. and Azeem, W. and Malik, A. A. and Jiang, H. and Ali, A. and Yang, J. and Liu, W.},
  journal = {Advanced Engineering Informatics},
  volume = {65},
  pages = {103284},
  year = {2025}
}

CVIU

STDepth: Leveraging semantic-textural information in transformers for self-supervised monocular depth estimation

X. Gao, B. Wang, Z. Ning, J. Yang, and W. Liu

Computer Vision and Image Understanding (CVIU), 2025

Bib

@article{gao2025stdepth,
  title = {STDepth: Leveraging semantic-textural information in transformers for self-supervised monocular depth estimation},
  author = {Gao, X. and Wang, B. and Ning, Z. and Yang, J. and Liu, W.},
  journal = {Computer Vision and Image Understanding (CVIU)},
  pages = {104422},
  year = {2025}
}

AAAI

Gim: A million-scale benchmark for generative image manipulation detection and localization

Y. Chen, X. Huang, Q. Zhang, W. Li, M. Zhu, Q. Yan, W. Liu, and J. Hu

In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025

Bib

@inproceedings{chen2025gim,
  title = {Gim: A million-scale benchmark for generative image manipulation detection and localization},
  author = {Chen, Y. and Huang, X. and Zhang, Q. and Li, W. and Zhu, M. and Yan, Q. and Liu, W. and Hu, J.},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025}
}

2024

TIP

Image Super-Resolution via Efficient Transformer Embedding Frequency Decomposition With Restart

Y. Zuo, W. Yao, Y. Hu, Y. Fang, W. Liu, and Y. Peng

IEEE Transactions on Image Processing (TIP), 2024

Bib

@article{zuo2024image,
  title = {Image Super-Resolution via Efficient Transformer Embedding Frequency Decomposition With Restart},
  author = {Zuo, Y. and Yao, W. and Hu, Y. and Fang, Y. and Liu, W. and Peng, Y.},
  journal = {IEEE Transactions on Image Processing (TIP)},
  year = {2024}
}

IJCV

Fast Image Smoothing via Quasi Weighted Least Squares

W. Liu, P. Zhang, H. Qin, and others

International Journal of Computer Vision (IJCV), 2024

Bib

@article{liu2024fast,
  title = {Fast Image Smoothing via Quasi Weighted Least Squares},
  author = {Liu, W. and Zhang, P. and Qin, H. and others},
  journal = {International Journal of Computer Vision (IJCV)},
  year = {2024}
}

TMM

Vb-kgn: Variational bayesian kernel generation networks for motion image deblurring

Y. Fu, X. Zhu, X. Li, X. Wang, X. Wu, S. Hu, and W. Liu

IEEE Transactions on Multimedia (TMM), 2024

Bib

@article{fu2024vbkgn,
  title = {Vb-kgn: Variational bayesian kernel generation networks for motion image deblurring},
  author = {Fu, Y. and Zhu, X. and Li, X. and Wang, X. and Wu, X. and Hu, S. and Liu, W.},
  journal = {IEEE Transactions on Multimedia (TMM)},
  year = {2024}
}

NeurIPS

Opus: occupancy prediction using a sparse set

J. Wang, Z. Liu, Q. Meng, L. Yan, K. Wang, J. Yang, W. Liu, Q. Hou, and M. M. Cheng

In Advances in Neural Information Processing Systems (NeurIPS), 2024

Bib

@inproceedings{wang2024opus,
  title = {Opus: occupancy prediction using a sparse set},
  author = {Wang, J. and Liu, Z. and Meng, Q. and Yan, L. and Wang, K. and Yang, J. and Liu, W. and Hou, Q. and Cheng, M. M.},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  volume = {37},
  pages = {119861--119885},
  year = {2024}
}

2023

ACM MM

Recurrent multi-scale transformer for high-resolution salient object detection

X. Deng, P. Zhang, W. Liu, and H. Lu

In Proceedings of the 31st ACM International Conference on Multimedia (ACM MM), 2023

Bib

@inproceedings{deng2023recurrent,
  title = {Recurrent multi-scale transformer for high-resolution salient object detection},
  author = {Deng, X. and Zhang, P. and Liu, W. and Lu, H.},
  booktitle = {Proceedings of the 31st ACM International Conference on Multimedia (ACM MM)},
  pages = {7413--7423},
  year = {2023}
}

AAAI

Softclip: Softer cross-modal alignment makes clip stronger

Y. Gao, J. Liu, Z. Xu, T. Wu, E. Zhang, K. Li, W. Liu, and X. Sun

In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023

Bib

@inproceedings{gao2023softclip,
  title = {Softclip: Softer cross-modal alignment makes clip stronger},
  author = {Gao, Y. and Liu, J. and Xu, Z. and Wu, T. and Zhang, E. and Li, K. and Liu, W. and Sun, X.},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
  pages = {1860--1868},
  year = {2023}
}

RAL

Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation

J. Liu, L. Kong, J. Yang, and W. Liu

IEEE Robotics and Automation Letters (RAL), 2023

Bib

@article{liu2023towards,
  title = {Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation},
  author = {Liu, J. and Kong, L. and Yang, J. and Liu, W.},
  journal = {IEEE Robotics and Automation Letters (RAL)},
  volume = {9},
  number = {1},
  pages = {763--770},
  year = {2023}
}

ECAI

Fastc: A fast attentional framework for semantic traversability classification using point cloud

Y. Chen, P. Wei, Z. Liu, B. Wang, J. Yang, and W. Liu

In European Conference on Artificial Intelligence (ECAI), 2023

Bib

@inproceedings{chen2023fastc,
  title = {Fastc: A fast attentional framework for semantic traversability classification using point cloud},
  author = {Chen, Y. and Wei, P. and Liu, Z. and Wang, B. and Yang, J. and Liu, W.},
  booktitle = {European Conference on Artificial Intelligence (ECAI)},
  pages = {429--436},
  year = {2023},
  publisher = {IOS Press}
}

2022

TPAMI

A generalized framework for edge-preserving and structure-preserving image smoothing

W. Liu, P. Zhang, Y. Lei, and others

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022

Bib

@article{liu2022generalized,
  title = {A generalized framework for edge-preserving and structure-preserving image smoothing},
  author = {Liu, W. and Zhang, P. and Lei, Y. and others},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  volume = {44},
  number = {10},
  pages = {6631--6648},
  year = {2022},
}

2021

TIP

Looking for the detail and context devils: High-resolution salient object detection

P. Zhang, W. Liu, Y. Zeng, and others

IEEE Transactions on Image Processing (TIP), 2021

Bib

@article{zhang2021looking,
  title = {Looking for the detail and context devils: High-resolution salient object detection},
  author = {Zhang, P. and Liu, W. and Zeng, Y. and others},
  journal = {IEEE Transactions on Image Processing (TIP)},
  volume = {30},
  pages = {3204--3216},
  year = {2021}
}

2020

AAAI

A Generalized Framework for Edge-Preserving and Structure-Preserving Image Smoothing

W. Liu, P. Zhang, Y. Lei, and others

In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020

Bib

@inproceedings{liu2020generalized,
  title = {A Generalized Framework for Edge-Preserving and Structure-Preserving Image Smoothing},
  author = {Liu, W. and Zhang, P. and Lei, Y. and others},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
  volume = {34},
  number = {7},
  pages = {11620--11628},
  year = {2020}
}

TOG

Real-time image smoothing via iterative least squares

W. Liu, P. Zhang, X. Huang, and others

ACM Transactions on Graphics (TOG), 2020

Bib

@article{liu2020realtime,
  title = {Real-time image smoothing via iterative least squares},
  author = {Liu, W. and Zhang, P. and Huang, X. and others},
  journal = {ACM Transactions on Graphics (TOG)},
  volume = {39},
  number = {3},
  pages = {1--24},
  year = {2020}
}

TIP

RAPNet: Residual atrous pyramid network for importance-aware street scene parsing

P. Zhang, W. Liu, Y. Lei, and others

IEEE Transactions on Image Processing (TIP), 2020

Bib

@article{zhang2020rapnet,
  title = {RAPNet: Residual atrous pyramid network for importance-aware street scene parsing},
  author = {Zhang, P. and Liu, W. and Lei, Y. and others},
  journal = {IEEE Transactions on Image Processing (TIP)},
  volume = {29},
  pages = {5010--5021},
  year = {2020}
}

TIP

Deep multiphase level set for scene parsing

P. Zhang, W. Liu, Y. Lei, and others

IEEE Transactions on Image Processing (TIP), 2020

Bib

@article{zhang2020deep,
  title = {Deep multiphase level set for scene parsing},
  author = {Zhang, P. and Liu, W. and Lei, Y. and others},
  journal = {IEEE Transactions on Image Processing (TIP)},
  volume = {29},
  pages = {4556--4567},
  year = {2020}
}

TITS

Semantic scene labeling via deep nested level set

P. Zhang, W. Liu, Y. Lei, and others

IEEE Transactions on Intelligent Transportation Systems (TITS), 2020

Bib

@article{zhang2020semantic,
  title = {Semantic scene labeling via deep nested level set},
  author = {Zhang, P. and Liu, W. and Lei, Y. and others},
  journal = {IEEE Transactions on Intelligent Transportation Systems (TITS)},
  volume = {22},
  number = {11},
  pages = {6853--6865},
  year = {2020}
}

Non-rigid object tracking via deep multi-scale spatial-temporal discriminative saliency maps

P. Zhang, W. Liu, D. Wang, and others

Pattern Recognition (PR), 2020

Bib

@article{zhang2020nonrigid,
  title = {Non-rigid object tracking via deep multi-scale spatial-temporal discriminative saliency maps},
  author = {Zhang, P. and Liu, W. and Wang, D. and others},
  journal = {Pattern Recognition (PR)},
  volume = {100},
  pages = {107130},
  year = {2020}
}

2019

TIP

Salient object detection with lossless feature reflection and weighted structural loss

P. Zhang, W. Liu, H. Lu, and others

IEEE Transactions on Image Processing (TIP), 2019

Bib

@article{zhang2019salient,
  title = {Salient object detection with lossless feature reflection and weighted structural loss},
  author = {Zhang, P. and Liu, W. and Lu, H. and others},
  journal = {IEEE Transactions on Image Processing (TIP)},
  volume = {28},
  number = {6},
  pages = {3048--3060},
  year = {2019}
}

Hyperfusion-Net: Hyper-densely reflective feature fusion for salient object detection

P. Zhang, W. Liu, Y. Lei, and others

Pattern Recognition (PR), 2019

Bib

@article{zhang2019hyperfusion,
  title = {Hyperfusion-Net: Hyper-densely reflective feature fusion for salient object detection},
  author = {Zhang, P. and Liu, W. and Lei, Y. and others},
  journal = {Pattern Recognition (PR)},
  volume = {93},
  pages = {521--533},
  year = {2019}
}

Deep gated attention networks for large-scale street-level scene segmentation

P. Zhang, W. Liu, H. Wang, and others

Pattern Recognition (PR), 2019

Bib

@article{zhang2019deep,
  title = {Deep gated attention networks for large-scale street-level scene segmentation},
  author = {Zhang, P. and Liu, W. and Wang, H. and others},
  journal = {Pattern Recognition (PR)},
  volume = {88},
  pages = {702--714},
  year = {2019}
}

2018

TCSVT

Embedding bilateral filter in least squares for efficient edge-preserving image smoothing

W. Liu, P. Zhang, X. Chen, and others

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2018

Bib

@article{liu2018embedding,
  title = {Embedding bilateral filter in least squares for efficient edge-preserving image smoothing},
  author = {Liu, W. and Zhang, P. and Chen, X. and others},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)},
  volume = {30},
  number = {1},
  pages = {23--35},
  year = {2018}
}

ICCV

Cascaded context pyramid for full-resolution 3D semantic scene completion

P. Zhang, W. Liu, Y. Lei, and others

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2018

Bib

@inproceedings{zhang2018cascaded,
  title = {Cascaded context pyramid for full-resolution 3D semantic scene completion},
  author = {Zhang, P. and Liu, W. and Lei, Y. and others},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year = {2018}
}

IJCAI

Salient object detection by lossless feature reflection

P. Zhang, W. Liu, H. Lu, and others

In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), 2018

Bib

@inproceedings{zhang2018salient,
  title = {Salient object detection by lossless feature reflection},
  author = {Zhang, P. and Liu, W. and Lu, H. and others},
  booktitle = {Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI)},
  pages = {1149--1155},
  year = {2018}
}

2017

TIP

Robust color guided depth map restoration

W. Liu, X. Chen, J. Yang, and others

IEEE Transactions on Image Processing (TIP), 2017

Bib

@article{liu2017robust,
  title = {Robust color guided depth map restoration},
  author = {Liu, W. and Chen, X. and Yang, J. and others},
  journal = {IEEE Transactions on Image Processing (TIP)},
  volume = {26},
  number = {1},
  pages = {315--327},
  year = {2017}
}

ICCV

Semi-global weighted least squares in image filtering

W. Liu, X. Chen, C. Shen, and others

In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017

Bib

@inproceedings{liu2017semiglobal,
  title = {Semi-global weighted least squares in image filtering},
  author = {Liu, W. and Chen, X. and Shen, C. and others},
  booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
  pages = {5861--5869},
  year = {2017}
}

TCSVT

Variable bandwidth weighting for texture copy artifact suppression in guided depth upsampling

W. Liu, X. Chen, J. Yang, and others

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2017

Bib

@article{liu2017variable,
  title = {Variable bandwidth weighting for texture copy artifact suppression in guided depth upsampling},
  author = {Liu, W. and Chen, X. and Yang, J. and others},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)},
  volume = {27},
  number = {10},
  pages = {2072--2085},
  year = {2017}
}

2016

ICIP

Robust weighted least squares for guided depth upsampling

W. Liu, X. Chen, J. Yang, and others

In IEEE International Conference on Image Processing (ICIP), 2016

Bib

@inproceedings{liu2016robust,
  title = {Robust weighted least squares for guided depth upsampling},
  author = {Liu, W. and Chen, X. and Yang, J. and others},
  booktitle = {IEEE International Conference on Image Processing (ICIP)},
  pages = {559--563},
  year = {2016}
}

2015

SPL

An MRF-based depth upsampling: Upsample the depth map with its own property

W. Liu, S. Jia, P. Li, and others

IEEE Signal Processing Letters (SPL), 2015

Bib

@article{liu2015mrf,
  title = {An MRF-based depth upsampling: Upsample the depth map with its own property},
  author = {Liu, W. and Jia, S. and Li, P. and others},
  journal = {IEEE Signal Processing Letters (SPL)},
  volume = {22},
  number = {10},
  pages = {1708--1712},
  year = {2015}
}

ICIP

Upsampling the depth map with its own properties

W. Liu, P. Li, J. Yang, and others

In IEEE International Conference on Image Processing (ICIP), 2015

Bib

@inproceedings{liu2015upsampling,
  title = {Upsampling the depth map with its own properties},
  author = {Liu, W. and Li, P. and Yang, J. and others},
  booktitle = {IEEE International Conference on Image Processing (ICIP)},
  pages = {3530--3534},
  year = {2015},
  organization = {IEEE}
}