邹琪

基本信息

教育背景

2001.9–2006.6，北京交通大学计算机与信息技术学院硕博连读

1997.9-2001.7，北京交通大学计算机与信息技术学院本科生

工作经历

• 2019.11-至今, 北京交通大学, 计算机与信息技术学院, 教授
  2013.12-2015.01, 美国Temple University, 计算机与信息科学系, 访问学者
  2012.10-2019.11, 北京交通大学, 计算机与信息技术学院, 副教授
  2006.6-2012.10, 北京交通大学, 计算机与信息技术学院, 讲师
  
  

研究方向

• 机器学习与认知计算
• 计算机技术
• 软件工程
• 人工智能
• 大数据技术与工程
• 智能感知与具身智能
• 新一代电子信息技术

研究生培养

主要研究方向为计算机视觉，主要围绕图像视频语义分析与理解展开相关研究，包括：多目标跟踪、姿态估计、轨迹预测、交互关系检测、以及视频预测等。

近年来在TIP、TMM、TCSVT、TNNLS、TITS等IEEE汇刊，以及CVPR、ECCV、AAAI、IJCAI,  ACM MM等视觉领域的CCF A类会议上发表多篇高水平论文。

欢迎感兴趣的本科生，准备 报考/推免 博士、硕士研究生 与我联系！

招生专业

• 计算机科学与技术硕士
• 计算机技术硕士
• 软件工程硕士
• 人工智能硕士
• 大数据技术与工程硕士
• 计算机科学与技术博士
• 新一代电子信息技术（含量子技术等）硕士
• 软件工程博士
• 新一代电子信息技术（含量子技术等）博士
• 人工智能博士
• 计算机技术博士

科研项目

1.主持北京市自然科学基金：恶劣天气下域泛化的轨道前向障碍物检测研究

2.主持河北省自然科学基金：基于场景动态建模的视频预测研究

3.主持国家自然科学基金：多目标跟踪中的注意模型研究

4.主持国家自然科学基金（青年科学基金项目）: 基于目标的注意模型及在图像分割和目标检测中的应用

5.主持北京市自然科学基金: 模拟初级视皮层的视觉表象模型与验证

6.主持：金融行业预测营销算法的研究与实践

7.主持 北京市青年英才计划“基于深度学习目标检测与图像分割”

8.主持  中央高校基本科研业务费项目“混合交通条件下的行人安全状态预警”

9.主持  中央高校基本科研业务费项目“监控视频中的人群轨迹预测研究”

10.参与国家自然科学基金面上项目，视知觉组织的神经计算模型

11.参与北京市自然基金“面上”，人脑记忆机制启发下的视觉信息的表达与存储

12. 参与科技部“863”基于视觉感知的智能计算模型及其关键技术研究

13.基本科研业务费重点项目: 基于计算机视觉的高速铁路运行环境感知与安全监测, 

14.国家自然科学基金“面上”: 基于高速前向运动视频的运行环境检测模型, 

15.北京交通大学: 铁路周界三维点云目标识别与分割算法

16.北京交通大学: 基于三维点云的铁路周界侵入植被快速检测算法

16.铁路生产运营大数据关键技术及典型应用研究

教学工作

北京交通大学优秀主讲教师

《C语言程序设计》

《图像分析与理解》

《计算机图形学》

论文/期刊

近年来在TPAMI、TIP、TMM、TCSVT、TNNLS等期刊，以及CVPR、AAAI、IJCAI、ACM MM、ECCV等会议上发表多篇高水平论文。

Zhiyuan Liu, Qi Zou*, Xixia Xu, Yanting Pei, Multi-Person Pose Estimation with Feature Enhancement and Decoupling based on Contrastive Learning. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2025.

Xiaoyu Chen, Chao Bai, ZhenyaoWu, Xinyi Wu, Qi Zou*, Yong Xia, Song Wang. Coarse-to-fine text injecting for realistic image super-resolution. Neurocomputing, 626 (2025): 129591.

Xixia Xu, Qi Zou*, Jiamao Li. Rethinking the Sparse End-to-End Multiperson Pose Estimation. IEEE Transactions on Systems, Man, and Cybernetics: Systems, Digital Object Identifier: 10.1109/TSMC.2024.352502, 2024

Lin, Xue , Q. Zou* , and  X. Xu . Human–object interaction detection via recycling of ground-truth annotations. Pattern Recognition 157: 110897, 2024 (CCF B)

Xixia Xu, Yingguo Gao, Xingjia Pan, Ke Yan, Xiaoyu Chen, and Qi Zou*, “Inter-image Contrastive Consistency for Multi-Person Pose Estimation.” The Proceedings of the 37th AAAI Conference on Artificial Intelligence, （AAAI）2023. (CCF A)

Qiu Lin, Zou Qi*, Self-training on Graph Neural Networks for Recommendation with Implicit Feedback, Knowledge-Based Systems,2023 (JCR-1区期刊)

Gao J, Zou Q, Zhao H: Multiple object tracking based on quadratic graph matching. IET Computer Vision (2023). https://doi.org/10.1049/cvi2.12185

2022 年
Xixia Xu, Qi Zou, Xue Lin. Adaptive Hypergraph Neural Network for Multi-person Pose Estimation. 36th AAAI Conference on Artificial Intelligence (AAAI) 2022 (CCF A类会议)

Xixia Xu; Yingguo Gao; Ke Yan; Xue Lin; Qi Zou; Location-free Human Pose Estimation, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 (CCF A 类会议)

Xixia Xu, Qi Zou, Xue Lin. Structure-enriched Topology Learning for Cross-domain Multi-person Pose estimation, IEEE Transactions on Multimedia 2022(JCR-1 区期刊)

Xiaoyu Chen, Qi Zou, Xixia Xu, Nan Wang. A Stronger Baseline for Seismic Facies Classification with Less Data, IEEE Trans. on Geoscience and Remote Sensing 2022 (JCR-2区期刊)

2021 年

X. Lin, Q. Zou, X. Xu, Y. Huang, D. Ding. Effects of Motion-relevant Knowledge from Unlabeled Video to Human-Object Interaction Detection. IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2021.313 1154, 2021. (JCR-1 区期刊)

Yanting Pei, Yaping Huang, Qi Zou, Xingyuan Zhang, Song Wang, “Effects of Image Degradation and Degradation Removal to CNN-based Image Classification”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(4): 1239-1253,  2021(JCR-1 区期刊)

Xue Lin, Qi Zou, Xixia Xu, Yaping Huang, Yi Tian, “Motion-Aware Feature Enhancement Network for Video Prediction”, IEEE Transactions on Circuits and Systems for Video Technology, 31(2): 688-700, 2021. ( JCR-1 区)

Nan Wang, Qi Zou, Yaping Huang, Qiulin Ma, Di Luan. A light tracker for online multiple pedestrian tracking[J]. Journal of Real-Time Image Processing. 18(1), 175-191, 2021. (JCR-3 区)

Nan Wang, Qi Zou, Qiulin Ma, Yaping Huang, Haitao Lou, An online multiple object tracker based on structure keeper net. Applied Intelligence. 51(11), 8010-8029，2021

Qiulin Ma; Qi Zou, Yaping Huang, Nan Wang. Dynamic pedestrian trajectory forecasting with LSTM-based Delaunay triangulation. Applied Intelligence. Doi: 10.1007/s10489-021-02562-5, 2021

Guo, Yaguang; Zou, Qi; Jin, Lu. A coarse to fine network for fast and accurate object detection in high-resolution images. IET Computer Vision, 15(4), 274-282, 2021

Xingyuan Zhang, Yaping Huang, Yang Mi, Yanting Pei, Qi Zou and Song Wang. “Video Sketch: A Middle-level Representation for Action Recognition”, Applied Intelligence, 51(4): 2589-2608, 2021

2020年

Xue Lin, Qi Zou, Xixia Xu. Action-guided Attention Mining and Relation Reasoning Network for Human-Object Interaction Detection[C]. International Joint Conference on Artificial Intelligence (IJCAI), 2020

Xu X , Zou Qi, Lin X. Alleviating Human-level Shift : A Robust Domain Adaptation Method for Multi-person Pose Estimation[C]. ACM Multimedia 2020.

Xixia Xu, Qi Zou, Xue Lin, Yaping Huang, Yi Tian. “Integral Knowledge Distillation for Multi-Person Pose Estimation”, IEEE Signal Processing Letters, doi: 10.1109/LSP.2020.2975426. 2020

Qiulin Ma; Qi Zou, Nan Wang; Qingji Guan; YantingPei. “Looking Ahead: Joint Small Group Detection and Tracking in Crowd Scenes Corresponding”, Journal of Visual Communication and Image Representation. 2020

艾鑫，邹琪，罗常津, 面向精确定位的列车车号文本定位与识别, 计算机辅助设计与图形学学报, 32（11）：1863-1870，2020年11月

王瑞, 李霄峰; 史天运; 邹琪. 基于视频深度学习的铁路周界入侵检测算法研究 . 交通运输系统工程与信息, 20(2): 61-68, 2020.

Xingyuan Zhang, Yaping Huang, Qi Zou, Yanting Pei, Runsheng Zhang and Song Wang, “A Hybrid Convolutional Neural Network for Sketch Recognition”, Pattern Recognition Letters, 130: 73-82, 2020

 Runsheng Zhang, Yaping Huang, Mengyang Pu, Jian Zhang, Qingji Guan, Qi Zou and Haibin Ling, "Object Discovery From a Single Unlabeled Image by Mining Frequent Itemsets With Multi-scale Features," IEEE Transactions on Image Processing, 29: 8606-8621, 2020

 张兴园，黄雅平，邹琪，裴艳婷，基于草图纹理和形状特征融合的草图识别，自动化学报，doi: 10.16383/j.aas.c200070, 2020

2019和Earlier

Qi Zou, Haibin Ling, Yu Pang; Yaping Huang and Mei Tian. “Joint Headlight Pairing and Vehicle Tracking by Weighted Set Packing in Nighttime Traffic Videos”, IEEE Transactions on Intelligent Transportation Systems, 19(6): 1950-1961, 2018.

Qi Zou, Haibin Ling, Siwei Luo, Yaping Huang and Mei Tian, “Robust Nighttime Vehicle Detection by Tracking and Grouping Headlights”, IEEE Transactions on Intelligent Transportation Systems, 16(5): 2838~2849, 2015.

Junbo Liu, Yaping Huang, Qi Zou, Mei Tian, Shengchun Wang,Xinxin Zhao and Peng Dai,"Learning Visual Similarity for Inspecting Defective Railway Fasteners", IEEE Sensors Journal, 19(16): 6844-6857, 2019

Junbo Liu, Yaping Huang, Qi Zou, and Shengchun Wang, “Learning Representative Features via Constrictive Annular Loss for Image Classification”, Applied Intelligence, 49(8): 3082-3092, 2019.

邹琪，罗四维,钟晶晶,杨利萍.Confidence shape metric for image segmentation[J]。Journal of Electronic Imaging，2013-05，2（22），1：13

邹琪，王哲,罗四维,黄雅平,田媚.A computational coding model for saliency detection in primary visual cortex[J]。Chinese Science Bulletin，2012-10，57（30），3943：3952

邹琪，赵松年,王哲,黄雅平.A neural computational model for bottom-up attention with invariant and overcomplete representation[J]。BMC Neuroscience，2012-12，13（13），145：181

黄雅平，赵嘉莉,刘蕴辉,罗四维,邹琪,田媚.Nonlinear dimensionality reduction using a temporal coherence principle[J]。Information Sciences，2011-05，16（181），3284：3307

邹琪，罗四维.全局显著结构主导下的知觉编组算法[J]。计算机学报，2007-12，30（11），

邹琪，罗四维.Multiresolution Image Perceptual Grouping using Topological Structure Embedded in Manifold[J]。International Journal of WMIP，2007-12，5（1），

邹琪，罗四维,郑宇.利用多尺度分析和编组的基于目标的注意计算模型[J]。《 电子学报 》，2006-12，34（3）

Wang Nan, Zou Qi*, Huang Yaping, Online Multiple Person Tracking using Fully-Convolutional Neural Networks and Motion Invariance Constraints, Lecture Notes in Computer Sciences. Chinese Conference on Pattern Recognition and Computer Vision (PRCV), Guangzhou, 2018.11.23-11.26.

Chengyue Sun, Qi Zou, Wei Fu and Jinqiao Wang. Multiple Hypersis based spatialtemporal Association  for Stable Pedestrian Counting, Lecture Notes in Computer Science, (PCM2013), 8294: 803-810,Dec.2013.

Mengyang Pu, Yaping Huang, Qingji Guan, Qi Zou,GraphNet: Learning Image Pseudo Annotations for Weakly-Supervised Semantic Segmentation. 26th ACM Multimedia 2018, (Oral)Seoul,South Korea,2018.10

Yanting Pei, Yaping Huang, Qi Zou, Yuhang Lu, Song Wang, “Does Haze Removal Help CNN-based Image Classification” 15th European Conference on Computer Vision, German, 2018.09.

黄雅平，赵嘉莉,田媚,邹琪.Slow Feature Discriminant Analysis and Its Application on Handwritten Digit Recognition。International Joint Conference on Neural Networks，Atlanta，2009-12

李燕，罗四维,邹琪.Directional balloon snake model based on curvature dependent magnitude。International Conference Signal and Image Processing，夏威夷，2009-12

钟晶晶，罗四维,邹琪.A Novel Measurement and Statistics of Similarity Cue for Edges in Contour Grouping。Proceedings of the International Conference on Signal Acquisition and Processing，Kuala Lumpur，2009-12

邹琪，罗四维.A Robust Unsupervised Algorithm of Contour Extraction。International conference on Signal Processing，北京，2008-12

邹琪，罗四维,黄雅平,李燕.Contour Grouping with Shape Manifold and Distance Transform。International conference on Pattern Recognition，佛罗里达州坦帕，2008-12

专著/译著

专利

软件著作权

获奖与荣誉

2013年 北京市青年英才计划

2016年北京交通大学计算机院青年教师教学基本功比赛一等奖

2018年北京交通大学握奇奖教金

2007年研究生优秀班主任

社会兼职

担任国际会议CVPR, ICCV, ECCV, ACCV审稿，教学部学位中心评审专家，期刊Pattern Recognition, CVIU，IEEE Trans. ITS等审稿人