姓名：吴斯

职称 / 职务：教授

主要研究领域：机器学习、机器视觉、大模型

所在团队：大数据与视觉计算团队

办公邮箱：cswusi@scut.edu.cn

办公室电话：无

个人简介：

吴斯，华南理工大学计算机科学与工程学院教授，博士生导师，中国人工智能学会机器学习专委会委员。发表高质量国际期刊和会议论文130余篇，其中JCR一区和CCF-A类论文80余篇；主持和参与国家自然科学基金、广东省自然科学基金等研究课题10余项。曾获2019年度广东省科技进步二等奖，指导研究生获得第七届中国国际“互联网+”大学生创新创业大赛产业赛道金奖。

教育经历：

2009-2012 香港城市大学博士

2006-2008华中科技大学硕士

2002-2006华中科技大学本科

工作经历：

2014-至今 华南理工大学计算机科学与工程学院副教授，教授

2013-2014 加拿大渥太华大学电气工程和计算机科学学院，博士后研究员

学术兼职：

课程教学（选填）：

模式识别（全英）

算法设计与分析

科研项目：无

代表性成果：

[1] Y. Zhang, J. Wang, Y. Huang, T. Chen, H. Wong, and S. Wu, “ClassBooth: boost class semantics with bidirectional feature fusion in text-to-image diffusion models,” IEEE Transactions on Multimedia, 2025.

[2] T. Chen, H. Fu, H. Wong, Y. Huang, S. Wu, Y. Xu, D. Wu, “3DMM-GAN: multi-modal alignment with adversarial learning for compositional 3D human image synthesis,” IEEE Transactions on Emerging Topics in Computational Intelligence, 2025.

[3] J. Zhang, X. Li, S. Wu, Y. Xu, and Y. Wang, “Prior-free augmentation for cloth-changing person re-identification,” ACM International Conference on Multimedia (MM), 2025.

[4] W. Chen, Z. Xu, R. Xu, S. Wu, and H. Wong, “Task-aware cross-model feature refinement transformer with large language models for visual grounding,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025. 

[5] L. Xie, B. Zheng, S. Wu, and H. Wong, “Dynamic content prediction with motion-aware priors for blind face video restoration,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

[6] T. Chen, Y. Zhang, L. Xie, W. Shen, S. Wu, and H. Wong, “SpotDiff: spatial gene expression imputation diffusion with single-cell RNA sequencing data integration,” AAAI Conference on Artificial Intelligence (AAAI), 2025.

[7] F. Xu, T. Chen, F. Yang, Y. Zhang, and S. Wu, “3DHumanEdit: multi-modal body part-aware conditioning information integration for 3D human manipulation,” AAAI Conference on Artificial Intelligence (AAAI), 2025.

[8] W. Xue, C. Ding, R. Xu, S. Wu, Y. Xu, and H. Wong, “RetouchGPT: LLM-based interactive high-fidelity face retouching via imperfection prompting,” AAAI Conference on Artificial Intelligence (AAAI), 2025.

[9] L. Xie, B. Zheng, W. Xue, Y. Zhang, L. Jiang, R. Xu, S. Wu, and H. Wong, “Discrete prior-based temporal-coherent content prediction for blind face video restoration,” AAAI Conference on Artificial Intelligence (AAAI), 2025.

[10] S. Pan, Y. Xu, R. Xu, Z. Zhou, S. Wu, and Z. Yu, “Self-correcting robot manipulation via Gaussian-splatted foresight,” AAAI Conference on Artificial Intelligence (AAAI), 2025.

[11] C. Liu, R. Li, S. Wu, H. Che, M. Leung, Z. Yu, and H. Wong, “Beyond Euclidean structures: collaborative topological graph learning for multi-view clustering,” IEEE Transactions on Neural Network and Learning Systems, 2024.

[12] L. Jiang, Y. Huang, L. Xie, W. Xue, C. Liu, S. Wu, and H. Wong, “Hunting blemishes: language-guided high-fidelity face retouching transformer with limited paired data,” ACM International Conference on Multimedia (MM), 2024.

[13] X. Wang, H. Gao, X. Wei, L. Peng, R. Li, C. Liu, S. Wu, and H. Wong, “Contrastive graph distribution alignment for partially view-aligned clustering,” ACM International Conference on Multimedia (MM), 2024.

[14] C. Liu, R. Li, H. Che, M. Leung, S. Wu, Z. Yu, and H. Wong, “Latent structure-aware view recovery for incomplete multi-view clustering,” IEEE Transactions on Knowledge and Data Engineering, 2024.

[15] L. Lin, W. Xue, X. Wei, W. Shen, C. Liu, S. Wu, and H. Wong, “SCTrans: Multi-scale scRNA-seq sub-vector completion transformer for gene-selective cell type annotation,” International Joint Conference on Artificial Intelligence (IJCAI), 2024.

[16] H. Gao, W. Shen, R. Li, C. Liu, and S. Wu, “Collaborative structure-preserved missing data imputation for single-cell RNA-Seq clustering,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2024.

[17] A. GNANHA, W. Cao, X. Mao, S. Wu, H. Wong, and Q. Li, “EviD-GAN: Improving GAN with an infinite set of discriminators at negligible cost,” IEEE Transactions on Neural Networks and Learning Systems, 2024.

[18] W. Wu, H. Wong, and S. Wu, “Pseudo-Siamese teacher for semi-supervised oriented object detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-14, 2024.

[19] L. Xie, B. Zheng, W. Xue, L. Jiang, S. Wu, C. Liu, and H. Wong, “Learning degradation-unaware representation with prior-based latent transformations for blind face restoration,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[20] W. Xue, L. Jiang, L. Xie, S. Wu, Y. Xu, and H. Wong, “VRetouchEr: learning cross-frame feature interdependence with imperfection flow for face retouching in videos,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[21] W. Wu, H. Wong, S. Wu, and T. Zhang, “Relational matching for weakly semi-supervised oriented object detection,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[22] F. Xu, R. Li, Si Wu, Y. Xu, and H. Wong, “Text-conditional attribute alignment across latent spaces for 3D controllable face image synthesis,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[23] F. Yang, T. Chen, X. He, Z. Cai, L. Yang, S. Wu, and G. Lin, “AttriHuman-3D: editable 3D human avatar generation with attribute decomposition and indexing,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[24] W. Xue, L. Xie, L. Jiang, T. Chen, S. Wu, C. Liu, and H. Wong, “RetouchFormer: semi-supervised high-quality face retouching transformer with prior-based selective self-attention,” AAAI Conference on Artificial Intelligence (AAAI), 2024.

[25] Q. Song, J. Li, S. Wu, and H. Wong, “A graph-based discriminator architecture for multi-attribute facial image editing,” IEEE Transactions on Multimedia, vol. 26, pp. 436-446, 2023.

[26] Y. Zhang, X. Huo, T. Chen, S. Wu, and H. Wong, “Exploring intra-class variation factors with learnable prompts for semi-supervised image synthesis,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

[27] L, Xie, W. Xue, Z. Xu, S. Wu, Z. Yu, and H. Wong, “Blemish-aware and progressive face retouching with limited paired data,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

[28] X, Wei, Z. Xu, C. Liu, S. Wu, Z. Yu, and H. Wong, “Text-guided unsupervised latent transformations for multi-attribute image manipulation,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

[29] W. Wu, S. Wu, and H. Wong, “Semi-supervised stereo-based 3D object detection via cross-view consensus,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

[30] C. Liu, R. Li, H. Che, S. Wu, D. Jiang, Z. Yu, and H. Wong, “Self-guided partial graph propagation for incomplete multi-view clustering,” IEEE Transactions on Neural Networks and Learning Systems, 2022

[31] C. Liu, S. Wu, R. Li, D. Jiang, and H. Wong, “Self-supervised graph completion for incomplete multi-view clustering,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 9, pp. 9394-9406, 2023.

[32] T. Chen, Y. Zhang, X. Huo, S. Wu, Y. Xu, and H. Wong, “SphericGAN: Semi-supervised hyper-spherical generative adversarial networks for fine-grained image synthesis,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

[33] C. Liu, S. Wu, D. Jiang, Z. Yu, and H. Wong, “View-aware collaborative learning for survival prediction and subgroup identification,” IEEE Transactions on Biomedical Engineering, vol. 70, no. 1, pp. 307-317, 2022.

[34] J. Zhong, X. Zeng, W. Cao, S. Wu, Z. Yu, and H. Wong, “Semi-supervised multiple choice learning for ensemble classification,” IEEE Transactions on Cybernetics, vol. 52, no. 5, pp. 3658-3668, 2022.

[35] C. Liu, W. Cao, S. Wu, W. Shen, D. Jiang, Z. Yu, and H. Wong, “Supervised graph clustering for cancer subtyping based on survival analysis and integration of multi-omic tumor data,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 19, no. 2, pp. 1193-1202, 2022.

[36] S. Lin, W. Wu, S. Wu, Y. Xu, and H. Wong, “Unreliable-to-reliable instance translation for semi-supervised pedestrian detection,” IEEE Transactions on Multimedia, vol. 24, pp. 728-738, 2022.

[37] C. Liu, W. Cao, S. Wu, W. Shen, D. Jian, Z. Yu, and H. Wong, “Asymmetric graph-guided multitask survival analysis with self-paced learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 2, pp. 654-666, 2022.

[38] T. Chen, Y. Liu, Y. Zhang, S. Wu, Y. Xu, L. Feng, and H. Wong, “Semi-supervised single-stage controllable GANs for conditional fine-grained image generation,” IEEE/CVF International Conference on Computer Vision (ICCV), 2021.

[39] G. Li, Y. Liu, X. Wei, Y. Zhang, S. Wu, Y. Xu, and H. Wong, “Discovering density-preserving latent space walks in GANs for semantic image transformations,” ACM International Conference on Multimedia (MM), 2021.

[40] T. Chen, S. Wu, X. Yang, Y. Xu, and H. Wong, “Semantic regularized class-conditional GANs for semi-supervised fine-grained image synthesis,” IEEE Transactions on Multimedia, vol. 24, pp. 2975-2985, 2022.

[41] H. Zhou, M. Azzam, J. Zhong, C. Liu, S. Wu, and H. Wong, “Knowledge exchange between domain-adversarial and private networks improves open set image classification,” IEEE Transactions on Image Processing, vol. 30, pp. 5807-5818, 2021.

[42] Y. Liu, X. Huo, T. Chen, X. Zeng, S. Wu, Z. Yu, and H. Wong, “Mask-embedded discriminator with region-based semantic regularization for semi-supervised class-conditional image synthesis,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[43] G. Li, Q. Jiao, S. Qian, S. Wu, and H. Wong, “High fidelity GAN inversion via prior multi-subspace feature composition,” in AAAI Conference on Artificial Intelligence (AAAI), 2021.

[44] M. Azzam, W. Wu, W. Cao, S. Wu, and H. Wong, “KTransGAN: variational inference-based knowledge transfer for unsupervised conditional generative learning,” IEEE Transactions on Multimedia, vol. 23, pp. 3318-3331, 2020.

[45] R. Li, W. Cao, H. Wong, and S. Wu, “Generating target image-label pairs for unsupervised domain adaptation,” IEEE Transactions on Image Processing, vol. 29, pp. 7997-8011, 2020.

[46] Y. Liu, G. Deng, X. Zeng, S. Wu, Z. Yu, and H. Wong, “Regularizing discriminative capability of CGANs for semi-supervised generative learning,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

[47] R. Li, Q. Jiao, W. Cao, H. Wong and S. Wu, “Model adaptation: unsupervised domain adaptation without source data,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

[48] S. Wu, W. Wu, S. Lei, S. Lin, R. Li, Z. Yu and H. Wong, “Semi-supervised human detection via region proposal networks aided by verification,” IEEE Transactions on Image Processing, vol. 29, pp. 1562-1574, 2020.

[49] J. Li, S. Wu, C. Liu, Z. Yu and H. Wong, “Semi-supervised deep coupled ensemble learning with classification landmark exploration,” IEEE Transactions on Image Processing, vol. 29, pp. 538-550, 2020.

[50] C. Liu, C. Zheng, S. Wu, Z. Yu, and H. Wong, “Multitask feature selection by graph-clustered feature sharing,” IEEE Transactions on Cybernetics, vol. 50, no. 1, pp. 74-86, 2020.