基本信息

个人简介

吴秋遐，女，博士，华南理工大学软件学院副研究员，硕士生导师。 IEEE 会员，曾担任IEEE SMC Guangzhou Chapter（IEEE 系统、人与控制论学会广州分会）秘书，先后担任 2015 年第二届及2016 年第三届复杂系统与控制研讨会的组织委员会委员及秘书长，现任广州市停车场行业协会智库专家。同时，凭借扎实的学术功底与行业洞察力，受邀担任多个国际顶尖期刊及会议的审稿人，包括 IEEE Transactions on Systems, Man, and Cybernetics（IEEE T SMC）、IEEE Transactions on Image Processing（IEEE TIP）等权威期刊，以及 AAAI（人工智能顶级会议）、MICCAI （医学影像计算领域顶会）、ACM MM（国际多媒体领域顶会）、ICASSP（国际声学、语音与信号处理顶会）等重要会议。

长期深耕智能算法与感知领域的研究与实践，在计算机视觉、生物特征识别、三维建模、智能感知、具身智能及智慧医疗等方向形成系统性技术积累，具备从底层算法研发到上层场景落地的全链条实战能力。从业以来，深度参与并主导多项核心软件与算法开发工作，累计以核心成员身份参与及主持国家级、省部级科研项目 20 余项，技术攻坚与项目统筹经验丰富。

作为项目主持人，牵头推进多项高量级科研课题，覆盖国家自然科学基金项目、人社部留学回国人员择优资助重点类项目、广东省自然科学基金项目及教育部中央高校基本科研业务费项目等，持续引领智能算法在前沿领域的技术探索。同时，积极推动技术成果转化，承接企事业单位委托的技术开发与信息化咨询项目，为企业提供定制化技术攻关方案，解决实际生产中的核心技术难题。

学术成果方面，在国际重要期刊及会议发表 EI/SCI 收录论文 50 余篇，其中多篇高水平研究成果入选人工智能领域顶级会议 AAAI，并凭借突破性研究贡献荣获 AAAI 杰出论文奖，学术影响力与技术创新性获领域高度认可。  

学历

2008-2012 华南理工大学自动化学院 工学博士，导师：邓飞其教授

2009-2011 澳大利亚悉尼大学信息技术学院 联合培养博士， 导师：Prof. David Dagan Feng

教学经历

数字逻辑、图像处理基础、专业方向前沿课

工作经历

2017.09-至今，华南理工大学，软件学院，副研究员

2016.03-2017.08， 华南理工大学，软件学院，助理研究员

2012.07-2016.03, 华南理工大学，广州现代产业技术研究院，助理研究员

社会兼职

IEEE会员，IEEE SMC Guangzhou Chapter秘书。作为主要成员参与了多个国际和国内会议的运作，担任2015年第二届复杂系统与控制研讨会、2016年第三届复杂系统与控制研讨会，组织委员会委员、秘书长，同时担任IEEE T SMC、NEUROCOMPUTING、IET IMAGE PROCESSING、IEEE SIGNAL PROCESSING LETTERS、DICTA等多个国际期刊会议审稿人。

研究方向

计算机视觉、生物特征识别、三维建模、智能感知、具身智能、智慧医疗等。

代表性论文

[1] Qiuxia Wu, Haipeng Deng, Kun Hu, Zhiyong Wang. (2025). Music source separation via hybrid waveform and spectrogram based generative adversarial network. Multim. Tools Appl., 84(31), 37655-37669.

[2] Kunming Su, Qiuxia Wu, Panpan Cai, Xiaogang Zhu, Xuequan Lu, Zhiyong Wang, Kun Hu. (2025). RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning. AAAI, 7015-7023.

[3] Zicheng Wang, Qiuxia Wu. (2025). WaveLoss: An Adaptive Dynamic Loss for Deep Gait Recognition. AAAI, 8259-8267. 

[4] Qiuxia Wu, Haiyang Huang, Kunming Su, Zhiyong Wang, Kun Hu. (2025). DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization. AAAI, 8441-8449. 

[5] Han Huang, Weiyi Chen, Qiuxia Wu, Huanjun Wang, Qian Cai, Yan Guo. (2025). T2WI-BCMIC: Non-Fat Saturated T2-Weighted Imaging Dataset for Bladder Cancer Muscle Invasion Classification. MICCAI, (13), 573-583. 

[6] Qiuxia Wu, Kunming Su. (2024). URINet: Unsupervised point cloud rotation invariant representation learning via semantic and structural reasoning. Comput. Vis. Image Underst., 248, 104136. 

[7] Qiuxia Wu, Zicheng Wang, Kunming Su, Sangni Xu. (2024). GSTNet: Gait Spatio-Temporal Network for Gait Recognition Using Millimeter-Wave Radar. ICASSP, 4855-4859. 

[8] Sangni Xu, Hao Xiong, Qiuxia Wu, Zhihui Wang, Shlomo Berkovsky, Zhiyong Wang. (2024). Fast Online Adaptation of Visual SLAM via Variational Information Transfer and Preservation. MMAsia, 51, 1-7.

[9] Feng Xiao, Hongbin Xu, Qiuxia Wu, Wenxiong Kang. (2024). SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph Attention. CoRR, abs/2403.08182.

[10] Xinpei Su, Qiuxia Wu. (2023). Multi-stages de-smoking model based on CycleGAN for surgical de-smoking. Int. J. Mach. Learn. Cybern., 14(11), 3965-3978.

[11] Haipeng Deng, Qiuxia Wu, Han Huang, Xiaowei Yang, Zhiyong Wang. (2023). InvolutionGAN: lightweight GAN with involution for unsupervised image-to-image translation. Neural Comput. Appl., 35(22), 16593-16605. 

[12] Haihong Xiao, Yuqiong Li, Wenxiong Kang, Qiuxia Wu. (2023). Distinguishing and Matching-Aware Unsupervised Point Cloud Completion. IEEE Trans. Circuits Syst. Video Technol., 33(9), 5160-5173.

[13] Zhongcheng Hong, Qiuxia Wu. (2023). Self-supervised monocular depth estimation via two mechanisms of attention-aware cost volume. Vis. Comput., 39(11), 5937-5951.

[14] Aoran Liu, Kun Hu, Wenxi Yue, Qiuxia Wu, Zhiyong Wang. (2023). Material-Aware Self-Supervised Network for Dynamic 3D Garment Simulation. ICME, 630-635.

[15] Sangni Xu, Hao Xiong, Qiuxia Wu, Tingting Yao, Zhihui Wang, Zhiyong Wang. (2023). Online Visual SLAM Adaptation against Catastrophic Forgetting with Cycle-Consistent Contrastive Learning. ICRA, 6196-6202.

[16] Wenxi Yue, Jing Zhang, Kun Hu, Qiuxia Wu, Zongyuan Ge, Yong Xia, Jiebo Luo, Zhiyong Wang. (2023). Part to Whole: Collaborative Prompting for Surgical Instrument Segmentation. CoRR, abs/2312.14481.

[17] Hongbin Xu, Weili Yang, Qiuxia Wu, Wenxiong Kang. (2022). Endowing rotation invariance for 3D finger shape and vein verification. Frontiers Comput. Sci., 16(5), 165332.

[18] Ruibin Gu, Qiuxia Wu, Yuqiong Li, Wenxiong Kang, Wing W. Y. Ng, Zhiyong Wang. (2022). Enhanced Local and Global Learning for Rotation-Invariant Point Cloud Representation. IEEE Multim., 29(4), 24-37.

[19] Ting Wang, Wing W. Y. Ng, Jinde Li, Qiuxia Wu, Shuai Zhang, Chris D. Nugent, Colin Shewell. (2022). A Deep Clustering via Automatic Feature Embedded Learning for Human Activity Recognition. IEEE Trans. Circuits Syst. Video Technol., 32(1), 210-223.

[20] Hongbin Xu, Lvequan Wang, Qiuxia Wu, Wenxiong Kang. (2021). PVLNet: Parameterized-View-Learning neural network for 3D shape recognition. Comput. Graph., 98, 71-81.

[21] Feng Xiao, Qiuxia Wu, Han Huang. (2021). Single-scale siamese network based RGB-D object tracking with adaptive bounding boxes. Neurocomputing, 451, 192-204.

[22] Ruibin Gu, Qiuxia Wu, Wing W. Y. Ng, Hongbin Xu, Zhiyong Wang. (2021). ERINet: Enhanced rotation-invariant network for point cloud classification. Pattern Recognit. Lett., 151, 180-186.

[23] Hongbin Xu, Zhipeng Zhou, Yu Qiao, Wenxiong Kang, Qiuxia Wu. (2021). Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation. AAAI, 3030-3038.

[24] Sangni Xu, Hao Xiong, Qiuxia Wu, Zhiyong Wang. (2021). Attention-based Long-term Modeling for Deep Visual Odometry. DICTA, 1-8.

[25] Ruibin Gu, Qiuxia Wu, Hongbin Xu, Wing W. Y. Ng, Zhiyong Wang. (2021). Learning Efficient Rotation Representation for Point Cloud via Local-Global Aggregation. ICME, 1-6.

[26] Jichao Kan, Kun Hu, Zhiyong Wang, Qiuxia Wu, Markus Hagenbuchner, Ah Chung Tsoi. (2021). Topic-Guided Local-Global Graph Neural Network For Image Captioning. ICME Workshops, 1-6.

[27] Hongbin Xu, Zhipeng Zhou, Yu Qiao, Wenxiong Kang, Qiuxia Wu. (2021). Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation. CoRR, abs/2104.05374.

[28] Feng Xiao, Qiuxia Wu. (2020). Visual saliency based global-local feature representation for skin cancer classification. IET Image Process., 14(10), 2140-2148.

[29] Weili Yang, Wei Luo, Wenxiong Kang, Zhixing Huang, Qiuxia Wu. (2020). FVRAS-Net: An Embedded Finger-Vein Recognition and AntiSpoofing System Using a Unified CNN. IEEE Trans. Instrum. Meas., 69(11), 8690-8701.

[30] Zhiteng Jian, Wenxi Yue, Qiuxia Wu, Wei Li, Zhiyong Wang, Vincent Lam. (2020). Multitask Learning for Video-based Surgical Skill Assessment. DICTA, 1-8.

[31] Su Tang, Shan Zhou, Wenxiong Kang, Qiuxia Wu, Feiqi Deng. (2019). Finger vein verification using a Siamese CNN. IET Biom., 8(5), 306-315.

[32] Bin Zhu, Lianfang Tian, Qiliang Du, Qiuxia Wu, Farisi Zeyad Sahl, Yao Yeboah. (2019). Adaptive dual fractional-order variational optical flow model for motion estimation. IET Comput. Vis., 13(3), 277-284.

[33] Linpu Fang, Guile Wu, Wenxiong Kang, Qiuxia Wu, Zhiyong Wang, David Dagan Feng. (2019). Feature covariance matrix-based dynamic hand gesture recognition. Neural Comput. Appl., 31(12), 8533-8546.

[34] Ruolin Liang, Qiuxia Wu, Xiaowei Yang. (2019). Multi-Pooling Attention Learning for Melanoma Recognition. DICTA, 1-6.

[35] Qiuxia Wu, Chih-Min Lin, Wubing Fang, Fei Chao, Longzhi Yang, Changjing Shang, Changle Zhou. (2018). Self-Organizing Brain Emotional Learning Controller Network for Intelligent Control System of Mobile Robots. IEEE Access, 6, 59096-59108.

[36] Yuxun Fang, Qiuxia Wu, Wenxiong Kang. (2018). A novel finger vein verification system based on two-stream convolutional network learning. Neurocomputing, 290, 100-107.

[37] Xinyi Lu, Yuxun Fang, Qiuxia Wu, Junhong Zhao, Wenxiong Kang. (2018). A Novel Multiple Distances Based Dynamic Time Warping Method for Online Signature Verification. CCBR, 645-652.

[38] Gengxing Wang, Wenxiong Kang, Qiuxia Wu, Zhiyong Wang, Junbin Gao. (2018). Generative Adversarial Network (GAN) Based Data Augmentation for Palmprint Recognition. DICTA, 1-7.

[39] Yuxun Fang, Wenxiong Kang, Qiuxia Wu, Lei Tang. (2017). A novel video-based system for in-air signature verification. Comput. Electr. Eng., 57, 1-14.

[40] Xinwei Qiu, Senping Tian, Wenxiong Kang, Wei Jia, Qiuxia Wu. (2017). Finger Vein Presentation Attack Detection Using Convolutional Neural Networks. CCBR, 296-305.

[41] Xiaobin Zhuang, Wenxiong Kang, Qiuxia Wu. (2016). Real-time vehicle detection with foreground-based cascade classifier. IET Image Process., 10(4), 289-296.

[42] Zhixing Huang, Wenxiong Kang, Qiuxia Wu, Junhong Zhao, Wei Jia. (2016). A Finger Vein Identification System Based on Image Quality Assessment. CCBR, 244-254.

[43] Lei Tang, Yuxun Fang, Qiuxia Wu, Wenxiong Kang, Junhong Zhao. (2016). Online Finger-Writing Signature Verification on Mobile Device for Local Authentication. CCBR, 409-416.

[44] Xuekui Yan, Wenxiong Kang, Feiqi Deng, Qiuxia Wu. (2015). Palm vein recognition based on multi-sampling and feature-level fusion. Neurocomputing, 151, 798-807.

[45] Dejian Li, Xishun Yue, Qiuxia Wu, Wenxiong Kang. (2015). CPGF: Core Point Detection from Global Feature for Fingerprint. CCBR, 224-232.

[46] Zeyi Huang, Wenxiong Kang, Qiuxia Wu, Xiaopeng Chen. (2014). A new descriptor resistant to affine transformation and monotonic intensity change. Comput. Vis. Image Underst., 120, 117-125.

[47] Wenxiong Kang, Qiuxia Wu. (2014). Contactless Palm Vein Recognition Using a Mutual Foreground-Based Local Binary Pattern. IEEE Trans. Inf. Forensics Secur., 9(11), 1974-1985.

[48] Wenxiong Kang, Qiuxia Wu. (2014). Pose-Invariant Hand Shape Recognition Based on Finger Geometry. IEEE Trans. Syst. Man Cybern. Syst., 44(11), 1510-1521.

[49] Qiuxia Wu, Zhiyong Wang, Feiqi Deng, Yong Xia, Wenxiong Kang, David Dagan Feng. (2013). Discriminative two-level feature selection for realistic human action recognition. J. Vis. Commun. Image Represent., 24(7), 1064-1074.

[50] Qiuxia Wu, Zhiyong Wang, Feiqi Deng, Zheru Chi, David Dagan Feng. (2013). Realistic Human Action Recognition With Multimodal Feature Selection and Fusion. IEEE Trans. Syst. Man Cybern. Syst., 43(4), 875-885.

[51] Kaimin Yu, Zhiyong Wang, Genliang Guan, Qiuxia Wu, Zheru Chi, David Dagan Feng. (2012). How Many Frames Does Facial Expression Recognition Require? ICME Workshops, 290-295.

[52] Qiuxia Wu, Shiyang Lu, Zhiyong Wang, Feiqi Deng, Wenxiong Kang, David Dagan Feng. (2011). Structure context of local features in realistic human action recognition. ICCV Workshops, 1496-1501.

[53] Qiuxia Wu, Zhiyong Wang, Feiqi Deng, David Dagan Feng. (2010). Realistic Human Action Recognition with Audio Context. DICTA, 288-293.