个人简介

裴文杰，哈尔滨工业大学（深圳）长聘副教授，博导，深圳市“海外高层次人才”， 代尔夫特理工大学（TU Delft）博士，卡内基梅隆大学（CMU）访问学者。 博士毕业于代尔夫特理工大学（Delft University of Technology）（理工科世界top 10）。师从 Dr. Laurens van der Maaten （Facebook AI Research） 和 Prof. David Tax (TU Delft)。主要从事计算机视觉和机器学习等领域的研究工作，特别在时序标注建模，图像视频文本描述，文本图像生成和图像修复等研究课题上取得了丰富的研究成果，在三大计算机视觉顶会（CVPR，ICCV，ECCV）以及IJCV, TIP, TVCG 等CCF A类顶级期刊和其他相关领域顶会上（NeurIPS, ACM MM, ACL）发表50多篇论文，并多次担任CVPR, ICCV, ECCV, ICML, NIPS, ICLR, AAAI, TIP, TMM, TNNLS等顶级会议和期刊审稿人。 裴文杰从2018年到2019年底在腾讯优图实验室担任计算机视觉高级研究员，并曾在飞利浦埃因霍温全球研发中心实习，并在2016年在美国卡内基梅隆大学(CMU，世界计算机专业排名第一)访问。 裴文杰与包括CMU，Facebook AI Research, TU Delft, Microsoft, 腾讯，香港科大，北航等国内外众多顶尖高校和企业科研部门的知名学者有密切学术合作。 裴文杰负责讲授两门本科专业核心课程，连续两年学生课程评教获得最高分A+。 教育经历 博士，Delft University of Technology 方向：计算机视觉和机器学习 导师：Laurens van der Maaten (Facebook AI Research) and David Tax (Delft University of Technology) 硕士， Eindhoven University of Technology 专业：计算机科学，方向：数据挖掘 导师：Toon Calders 硕士，浙江大学 专业：计算机科学，方向：计算机图形学 导师：鲍虎军教授，黄劲教授 本科，上海交通大学 专业：计算机科学与技术 工作经历 2022 - 现在 长聘副教授，哈尔滨工业大学（深圳） 2020 - 2021 助理教授， 哈尔滨工业大学（深圳） 2018 - 2019 腾讯优图X-Lab，计算机视觉高级研究员 Working with 贾佳亚教授，Yu-Wing Tai 教授 2016， 卡内基梅陇大学（CMU）， 访问学者 Working with Louis-Philippe Morency, Tadas Baltru？aitis

研究领域

计算机视觉,机器学习

1）Sequence Modeling: 时序标注建模，有效提取各种时序序列数据特征，例如视频，语音，文本等 2）Applications of Sequence Modeling: 时序建模具体应用，包括 （1）Tracking: 目标跟踪，包括2D/3D跟踪 （2）Video Understanding: 视频理解 （3）Captioning: 图像视频文本描述生成 3）AIGC, 图像内容生成，包括 （1）Image Restoration: 图像复原 （2）Text-to-Image Synthesis 基于文本的图像可控生成 （3）Image Super-resolution: 图像超分 （4）Image Inpainting: 图像填充 4）小样本，弱监督下的Image detection/segmentation/recognition: 图像检测/分割/识别 （1）小样本目标检测 （2）小样本目标分割 （3）小样本分类 （3）Person Re-ID, pedestrian detection: 行人重识别、行人检测 （4）OCR, 图像文本检测与识别 （5）弱监督目标检测 （6）弱监督OCR 5）3D Vision （1）3D 小样本目标分割 （2）Nerf-related research topics，like Interactive 3D segmentation of Radiance Fields （3）3D 点云跟踪 6) Others (1) Modeling of Graph Neural Networks: 图神经网络

近期论文

查看导师新发文章 （温馨提示：请注意重名现象，建议点开原文通过作者单位确认）

Xin Feng#, Yifeng Xu#, Guangming Lu*, Wenjie Pei*. Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection, ICCV, 2023. (CCF A，清华分区A，计算机视觉Top顶会) （共同一作为哈工大博士和哈工大本科生） Zhenhua Ning#, Zhuotao Tian#, Guangming Lu, Wenjie Pei*. Boosting Few-shot 3D point cloud segmentation via query-guided enhancement. ACM MM, 2023. (CCF A，清华分区A，计算机多媒体Top顶会) （一作为哈工大硕士） Huimin Zeng, Weinong Wang, Xin Tao, Zhiwei Xiong, Yu-Wing Tai, Wenjie Pei*. Feature Decoupling-Recycling Network for Fast Interactive Segmentation, ACM MM, 2023. (CCF A，清华分区A，计算机多媒体Top顶会) （一作为中科大博士） Songlin Tang, Wenjie Pei*, Xin Tao, Tanghui Jia, Guangming Lu, Yu-Wing Tai. Scene-generalizable Interactive Segmentation of Radiance Fields, ACM MM, 2023. (CCF A，清华分区A，计算机多媒体Top顶会) （一作为哈工大硕士） Jin Li, Di Kang, Wenjie Pei, Xuefei Zhe, Ying Zhang, Linchao Bao, Zhenyu He. Audio2Gestures: Generating Diverse Gestures from Audio. TVCG, 2023. (CCF A，清华分区A，中科院一区，计算机图形学Top顶刊)（一作为哈工大博士） Xin Li#, Wenjie Pei#, Zikun Zhou, Zhenyu He, Huchuan Lu, Ming-Hsuan Yang. Self-Supervised Tracking via Target-Aware Data Synthesis. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023. (中科院一区，模式识别顶刊) Wenjie Pei, Xin Feng, Canmiao Fu, Qiong Cao, Guangming Lu, Yu-Wing Tai. Learning Sequence Representations by Non-local Recurrent Neural Memory, IJCV, 2022. (CCF A，清华分区A，计算机视觉Top顶刊) Jing Xu, Xu Luo, Xinglin Pan, Wenjie Pei, Yanan Li, Zenglin, Xu. Alleviating the Sampling Bias of Few Shot Data by Removing Projection to the Centroid, NeurIPS, 2022. (CCF A，清华分区A, 机器学习顶会) (一作为哈工大博士生) Qi Fan, Wenjie Pei*, Yu-Wing Tai, Chi-Keung Tang. Self-Support Few-Shot Semantic Segmentation, ECCV, 2022. (计算机视觉顶会，清华分区A) （一作为港科大博士生） Shuang Wu, Wenjie Pei*, Dianwen Mei, Fanglin Chen, Jiandong Tian, Guangming Lu*. Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection. ECCV, 2022. (计算机视觉顶会，清华分区A) （一作为哈工大硕士生） Wenjie Pei, Shuang Wu, Dianwen Mei, Fanglin Chen, Jiandong Tian, Guangming Lu. Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations. ECCV, 2022. (计算机视觉顶会，清华分区A) （共一为哈工大硕士生） Chaozheng Wang, Shuzheng Gao, Pengyun Wang, Cuiyun Gao, Wenjie Pei, Lujia Pan, Zenglin Xu. Label-Aware Distribution Calibration for Long-tailed Classification. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022. (中科院一区，模式识别顶刊) (一作为哈工大硕士生) Fengjun Li, Xin Feng, Fanglin Chen, Guangming Lu, Wenjie Pei*. Learning Generalizable Latent Representations for Novel Degradations in Super-Resolution. ACM MM, 2022. (CCF A，清华分区A，多媒体顶会) （一作为哈工大硕士生） JingJing Wu, Pengyuan Lyu, Guangming Lu, Chengquan Zhang, Kun Yao, Wenjie Pei*. Decoupling Recognition from Detection: Single Shot Self-Reliant Scene Text Spotter. ACM MM, Oral, 2022. (CCF A，清华分区A，多媒体顶会) （一作为哈工大硕士生） Zebin Lin, Wenjie Pei*, Fanglin Chen, Guangming Lu*. Pedestrian Detection by Exemplar-Guided Contrastive Learning. IEEE Transactions on Image Processing (TIP), 2022. (CCF A，清华分区A，中科院一区, 计算机视觉顶刊) （一作为哈工大硕士生） Zikun Zhou, Jianqiu Chen, Wenjie Pei*, Kaige Mao, Hongpeng Wang, Zhenyu He*. Global Tracking via Ensemble of Local Trackers. CVPR, 2022. (CCF A，清华分区A，计算机视觉顶会) （一作为哈工大博士生） Bin Liang, Chenwei Lou, Xiang Li, Min Yang, Lin Gui, Yulan He, Wenjie Pei, Ruifeng Xu. Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network. ACL, 2022. (CCF A，清华分区A，自然语言处理顶会) （一作为哈工大博士生） Zengwei Yao, WenjiePei*, Fanglin Chen, Guangming Lu*, David Zhang. Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain. IEEE Transactions on Audio, Speech, and Language Processing (TASLP), 2021. (计算机语音识别顶刊, 清华分区A，中科院一区) （一作为哈工大硕士生） Zikun Zhou, WenjiePei*, Xin Li, Hongpeng Wang, Feng Zheng, Zhenyu He*. Saliency-Associated Object Tracking. International Conference on Computer Vision (ICCV), 2021. (CCF A，清华分区A，计算机视觉顶会) （一作为哈工大博士生） Jing Li, Di Kang, WenjiePei, Xuefei Zhe, Ying Zhang, Zhenyu He, Linchao Bao. Audio2Motion: Generating Diverse Human Motion from Audio with Conditional Variational Autoencoders. International Conference on Computer Vision (ICCV), 2021. (CCF A，清华分区A，计算机视觉顶会) （一作为哈工大博士生） Xin Feng, Wenjie Pei*, Zihui Jia, Fanglin Chen, David Zhang, Guangming Lu*. Deep-Masking Generative Network: A Unified Framework for Background Restoration from Superimposed Images. Transactions on Image Processing (TIP) (Impact Factor: 9.34), 2021. (CCF A，清华分区A，中科院一区，计算机视觉顶刊) （一作为哈工大博士生） Kai Yang, Zhenyu He*, Wenjie Pei*, Zikun Zhou, Xin Li, Di Yuan, Haijun Zhang. SiamCorners: Siamese Corner Networks for Visual Tracking. Transactions on Multimedia (TMM) (Impact Factor: 5.45), 2021. (清华分区A，中科院一区，计算机多媒体顶刊) （一作为哈工大博士生） Weinong Wang, Wenjie Pei*, Qiong Cao, Shu Liu, Guangming Lu and Yu-wing Tai. Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification. Transactions on Image Processing (TIP) (Impact Factor: 9.34), 2021. (CCF A，清华分区A，中科院一区，计算机视觉顶刊) （一作为腾讯前同事） Yi Li, Wenjie Pei*, Zhenyu He*. SRHEN: Stepwise-Refining Homography Estimation Network via Parsing Geometric Correspondence in Deep Latent Space. ACM MM, 2020. (计算机多媒体顶会，CCF A，清华分区A) （一作为哈工大博士生） Qi Fan, Lei Ke, Wenjie Pei*, Chi-Keung Tang and Yu-Wing Tai. Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation. ECCV, 2020. (计算机视觉顶会，清华分区A) （一作为港科大博士生） Jiadong Liang#, Wenjie Pei# and Feng Lu. CPGAN: Content-Parsing Generative Adersarial Networks for Text-to-Image Synthesis. ECCV, Spotlight (5% acceptance rate), 2020. (计算机视觉顶会，清华分区A). （一作为北航博士生） Wenjie Pei, Hamdi Dibeklio？lu, Tadas Baltru？aitis and David M.J. Tax. Attended End-to-end Architecture for Age Estimation from Facial Expression Videos. Transactions on Image Processing (TIP) (Impact Factor: 9.34), 2020. (CCF A，清华分区A，中科院一区，计算机视觉顶刊) Canmiao Fu#, WenjiePei#, Qiong Cao, Chaopeng Zhang, Xiaoyong Shen, Yong Zhao and Yu-wing Tai. Non-local Recurrent Neural Memory for Supervised Sequence Modeling. International Conference on Computer Vision (ICCV) Oral (4.3% acceptance rate), 2019. (CCF A，清华分区A，计算机视觉顶会) （一作为腾讯实习生） Lei Ke, Wenjie Pei, Ruiyu Li, Xiaoyong Shen and Yu-wing Tai. Reflective Decoding Network for Image Captioning. International Conference on Computer Vision (ICCV), 2019. This work is conducted by my intern Lei Ke under my supervision. (CCF A，清华分区A，计算机视觉顶会) （一作为港科大博士生） Wenjie Pei, Jiyuan Zhang, Xiangrong Wang, Lei Ke, Xiaoyong Shen and Yu-wing Tai. Memory-Attended Recurrent Network for Video Captioning. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. (CCF A，清华分区A，计算机视觉顶会) Wenjie Pei, Hamdi Dibeklio？lu, David MJ Tax and Laurens van der Maaten. Multivariate Time Series Classification using the Hidden-Unit Logistic Model. IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (Impact Factor: 8.79), 2018. (中科院一区，模式识别顶刊) Wenjie Pei#, Jie Yang#, Zhu Sun, Jie Zhang, Alessandro Bozzon and David MJ Tax (#Equal contribution). Interacting Attention-gated Recurrent Networks for Recommendation. ACM International Conference on Information and Knowledge Management (CIKM), full paper, 2017. (CCF B类) Wenjie Pei, Tadas Baltru？aitis, David M.J. Tax and Louis-Philippe Morency. Temporal Attentijon-Gated Model for Robust Sequence Classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. (CCF A，清华分区A，计算机视觉顶会)