谢源

谢源，现任bwin官网登录入口教授、博导，国家优青，闽江学者讲座教授，人社部“香江学者”。于2010年和2013年分别获得厦门大学计算机系和中国科学院自动化所工学硕士和博士学位。2014年获国家人社部和博管会的资助，授予“香江学者”的称号，赴香港理工大学计算机系从事两年的博士后研究工作。历任中国科学院自动化研究所助理研究员（2013）和副研究员（2016）。

    主要研究方向为计算机视觉和机器学习，当前研究方向涵盖：低层视觉、面向自动驾驶的三维感知、跨模态感知、跨模态学习、小样本学习、大模型持续学习等。先后主持了国家自然科学基金优秀青年基金、科技部科技创新2030“新一代人工智能”重大项目课题，国家自然科学基金面上项目，青年项目，人力资源与社会保障部“香江学者”，上海市人工智能科技支撑专项，北京市和上海市自然科学基金面上项目各1项，第一、二届中国人工智能学会-华为MindSpore学术基金。在国内外权威期刊和顶级会议上共发表和接收学术论文100余篇，其中第一作者/通讯作者CCF A类或中科院一区论文80余篇。申请人提出的从向量到张量的正则化理论及方法已逐渐得到国内外众多同行的认可，相关成果Google引用近万次（引用超百次的论文18篇），提出的图像复原算法获得了CVPR2020图像视频复原和增强挑战赛（IEEE CVPR NTIRE 2020）的图像去雾和去摩尔纹赛道的两项冠军；先后担任图像处理领域顶级期刊IEEE TIP编委（Associated Editor），IJCAI2019-2022的领域主席/Senior PC，CIKM2019领域主席；相关研究成果获得了吴文俊人工智能科学技术奖自然科学二等奖（第二完成人）、上海市科技进步特等奖（第十完成人）、福建省自然科学二等奖（第二完成人）。

国际人工智能顶级学术会议IJCAI资深程序委员会委员（SPC），数据挖掘权威学术会议CIKM资深程序委员会委员（SPC），国际期刊International Journal of Image and Graphics编委。中国自动化学会混合智能专委会委员。顶级和权威期刊和会议审稿人，期刊如IJCV、IEEE TIP、TNNLS、TGRS、TSP、TCYB、TII、TCSVT、TMM等，会议如ICCV2015、ICCV2017、ICIP2015、ICONIP2012等。

人工智能；计算机视觉；机器学习

深度学习基础与导论（本科课程）

计算机视觉与深度学习（博士生课程）

News:

I have been designated as the Associate Editor of the top journal IEEE Transactions on Image Processing.

有多个2025年秋入学的博士名额，对Foundation Model和Embodied AI感兴趣的同学，欢迎联系：yxie@cs.ecnu.edu.cn

------------------------------------------------2024-----------------------------------------------------

One paper has been accepted by TPAMI, one paper has been accepted by TIP, one paper has been accepted by ICLR2024, one paper has been accepted by NeurIPS2024, four papers have been accepted by CVPR2024, and eight papers have been accepted by AAAI2024:

[1] Xudong Tian#, Zhizhong Zhang#, Cong Wang, Wensheng Zhang, Yanyun Qu, Lizhuang Ma, Zongze Wu, Yuan Xie*, Dacheng Tao. Variational Distillation for Multi-View Learning, IEEE TPAMI, 2024.

[2] Tianfang Sun, Zhizhong Zhang*, Xin Tan, Yanyun Qu, Yuan Xie. Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning, IEEE TIP, 2024.

[3] Jingyang Qiao#, Zhizhong Zhang#, Xin Tan, Chengwei Chen, Yanyun Qu, Yong Peng, Yuan Xie*. Prompt Gradient Projection for Continual Learning, ICLR, 2024. Spotlight

[4] Xiaotong Luo, Yuan Xie, Yanyun Qu. Learning Re-sampling Methods with Parameter Attribution for Image Super-resolution, NeurIPS, 2023.

[5] Haoming Chen, Zhizhong Zhang#, Yanyun Qu, Ruixin Zhang, Xin Tan, Yuan Xie*. Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception, CVPR, 2024.

[6] Qihang Ma#, Xin Tan#, Yanyun Qu, Lizhuang Ma, Zhizhong Zhang*, Yuan Xie. COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction, CVPR, 2024.

[7] Zhen Zhao, Jingqun Tang, Chunhui Lin, Binghong Wu, Can Huang, Hao Liu, Xin Tan, Zhizhong Zhang*, Yuan Xie. Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer, CVPR, 2024.

[8] Xiaofan Li, Zhizhong Zhang, Xin Tan*, Yanyun Qu, Chengwei Chen, Yuan Xie, Lizhuang Ma. PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection, CVPR, 2024.

[9] Hongquan Zhang, Bin-Bin Gao, Yi Zeng, Xudong Tian, Xin Tan, Zhizhong Zhang*, Yanyun Qu, Jun Liu, Yuan Xie. Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection, AAAI, 2024.

[10] Yujun Chen, Xin Tan*, Zhizhong Zhang, Yanyun Qu, Yuan Xie. Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation, AAAI, 2024.

[11] Lianggangxu Chen, Youqi Song, Yiqing Cai, Jiale Lu, Yang Li, Yuan Xie, Changbo Wang, Gaoqi He*. Multi-Prototype Space Learning for Commonsense-based Scene Graph Generation, AAAI, 2024.

[12] Xiaotong Luo, Yuan Xie, Yanyun Qu*, Yun Fu. SkipDiff: Adaptive Skip Diffusion Model for High-Fidelity Perception Image Super-resolution, AAAI, 2024.

[13] Jiangming Shi, Shanshan Zheng, Xiangbo Yin, Yang Lu, Yuan Xie, Yanyun Qu*. CLIP-guided Federated Learning on Heterogeneity and Long-Tailed Data, AAAI, 2024.

[14] Yachao Zhang, Runze Hu, Ronghui Li, Yanyun Qu, Yuan Xie, Xiu Li. Cross-Modal Match for Language Conditioned 3D Object Grounding, AAAI, 2024.

[15] Yubo Zhou, Jin Lin, Fangchen Ye, Yanyun Qu*, Yuan Xie. Efficient Lightweight Image Denoising with Triple Attention Transformer, AAAI, 2024.

[16] Xiaotong Luo, Zekun Ai, Qiuyuan Liang, Yuan Xie, Yanyun Qu, Yun Fu. AdaFormer: Efficient Transformer with Adaptive Token Sparsification for Image Super-resolution, AAAI, 2024.

------------------------------------------------2023-----------------------------------------------------

Two papers have been accepted by TPAMI, three papers have been accepted by ICCV2023, and fours papers have been accepted by ACMMM2023:

[1] Yongqiang Tang, Yuan Xie*, Wensheng Zhang. Affine Subspace Robust Low-Rank Self-Representation: From Matrix to Tensor, IEEE TPAMI, 2023.

[2] Xin Tan, Qihang Ma, Jingyu Gong, Jiachen Xu, Zhizhong Zhang, Haichuan Song, Yanyun Qu, Yuan Xie*, Lizhuang Ma. Positive-Negative Receptive Field Reasoning for Omni-supervised 3D Segmentation, IEEE TPAMI, 2023.

[3] Xudong Tian, Zhizhong Zhang, Xin Tan, Jun Liu, Chengjie Wang, Yanyun Qu, Guannan Jiang, Yuan Xie*. Instance and Category Supervision are Alternate Learners for Continual Learning, ICCV, 2023.

[4] Zhiwei Zhang, Qian Yu, Chengyang Li, Jia Cai, Ran Yi, Yuan Xie*, Lizhuang Ma*. LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment, ICCV, 2023.

[5] Jiangming Shi, Yachao Zhang, Xiangbo Yin, Yuan Xie*, Zhizhong Zhang, Jianping Fan, Zhongchao Shi, Yanyun Qu*. Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification, ICCV, 2023.

[6] Yao Wu, Mingwei Xing, Yachao Zhang, Yuan Xie*,Jianping Fan, Zhongchao Shi, Yanyun Qu*. Cross-modal Unsupervised Domain Adaptation for 3D Semantic Segmentation via Bidirectional Fusion-then-Distillation. ACMMM, 2023.

[7] Zhong Chen, Zhizhong Zhang*, Xin Tan, Yanyun Qu, Yuan Xie*. Unveiling the Power of CLIP in Unsupervised Visible-Infrared Person Re-Identification. ACMMM, 2023.

[8] Xu Huang, Jin Liu, Zhizhong Zhang, Yuan Xie. Improving Cross-Modal Recipe Retrieval with Component-Aware Prompted CLIP Embedding. ACMMM, 2023.

[9] Fangchen Ye, Jin Lin, Hongzhan Huang, Jianping Fan, Zhongchao Shi, Yuan Xie*, Yanyun Qu*. Hardware-friendly Scalable Image Super-Resolution with Progressive Structured Sparsity. ACMMM, 2023.

Three papers have been accepted by CVPR2023, three papers have been accepted by AAAI2023, and one paper has been accepted by IJCAI2023:

[1] Zhen Zhao, Zhizhong Zhang*, Xin Tan, Jun Liu, Yanyun Qu, Yuan Xie*, Lizhuang Ma. Rethinking Gradient Projection Continual Learning: Stability/Plasticity Feature Space Decoupling. CVPR, 2023.

[2] Tenghao Cai, Zhizhong Zhang, Xin Tan, Yanyun Qu, Guannan Jiang, Chengjie Wang, Yuan Xie*. Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference. CVPR, 2023.

[3] Jin Lin, Xiaotong Luo, Ming Hong, Yanyun Qu, Yuan Xie*, Zongze Wu. Memory-friendly Scalable Super-resolution via Rewinding Lottery Ticket Hypothesis. CVPR, 2023.

[4] Yuxiang Lan, Yachao Zhang, Yanyun Qu, Cong Wang, Yuan Xie*, Zongze Wu. Weakly Supervised 3D Segmentation via Receptive-driven Pseudo Label Consistency and Structural Consistency, AAAI, 2023.

[5] Yanbo Wang, Chuming Lin, Donghao Luo, Ying Tai, Zhizhong Zhang*, Yuan Xie. High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets. AAAI, 2023.

[6] Jinxiang Lai, Siqian Yang, Wenlong Wu, Guannan Jiang, Xi Wang, Jun Liu, Bin-Bin Gao, Wei Zhang, Yuan Xie*, Chengjie Wang. SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning. AAAI, 2023.

[7] Xiaofan Li, Yachao Zhang, Shiran Bian, Yanyun Qu, Yuan Xie, Zhongchao Shi, Jianping Fan. VS-Boost: Boosting Visual-Semantic Association for Generalized Zero-Shot Learning. IJCAI, 2023.

国家自然科学基金优秀青年基金获得者；

重庆市杰出青年基金获得者；

2022年度福建省自然科学二等奖（排名第二）；

中国智能科学最高奖 2020吴文俊人工智能科学技术奖自然科学二等奖（排名第二）；

2020上海市科技进步特等奖（排名第十）；

人力资源与社会保障部“香江学者”奖（排名第一）