目录
硕士报考志愿采集    更新日期:2024年4月2日
姓 名 张姗姗 性 别
出生年月 1987年5月 籍贯 江西黎川县
民 族 汉族 政治面貌 中国共产党党员
最后学历 博士研究生 最后学位 理学博士
技术职称 教授 导师类别 博士生导师
导师类型 校内 兼职导师
行政职务 Email shanshan.zhang@njust.edu.cn
工作单位 计算机科学与工程学院 邮政编码 210094
通讯地址 南京市孝陵卫200号
单位电话 025-84315017-4036
个人主页 https://shanshanzhang.github.io/
指导学科
学科专业(主) 0812|计算机科学与技术 招生类别 博、硕士 所在学院 计算机科学与工程学院
研究方向

计算机视觉,模式识别,深度学习,特别关注面向无人驾驶的环境感知技术。

工作经历
• 2016.12 至今: 南京理工大学 教授
 
• 2018.04-2018.06: 美国加州大学伯克利分校 访问学者
 
• 2015.01-2016.12: 德国马普计算机研究所 博士后
 
• 2014.09-2014.12: 德国马普计算机研究所 访问学者
 
• 2010.06-2010.09: 日本国立情报学研究所 访问学者
教育经历
• 2011.09-2015.02: 德国波恩大学(Top100)计算机系 博士
 
• 2004.09-2011.03: 同济大学 电信学院 本科&硕士
获奖、荣誉称号

• 国家优青,2023

• 江苏省杰青,2023

• 中国图象图形学学会石青云女科学家奖,2021

• 中国科协“青年人才托举计划”,2018

• 微软“铸星学者计划”,2018

• 中国人工智能学会-华为MindSpore学术奖励基金,2022 

• “CCF-腾讯犀牛鸟基金”奖励,2018 

• 德语区(德国、瑞士、奥地利)计算机学会最佳博士论文提名,2015

社会、学会及学术兼职

• IEEE 会员、Computer Vision Foundation (CVF)会员

• 中国人工智能学会CAAI会员、模式识别专委会副秘书长

• 中国计算机学会CCF会员、计算机视觉专委会委员(青年工作组委员)

• 江苏省人工智能学会会员、模式识别专委会委员

• 视觉与学习青年学者研讨会VALSE常务AC

• 模式识别权威期刊Pattern Recognition编委

• 审稿人: T-PAMI, IJCV, T-IP, T-NNLS, T-ITS, T-CSVT, T-MM, PR等顶级期刊

• 程序委员会委员: CVPR, ICCV, ECCV, AAAI, IJCAI等顶级会议

科研项目
• 基于异质任务耦合的鲁棒视觉行人搜索(2022/01-2025/12)

   国家自然科学基金面上项目(主持)

• 视频中人体检测、再识别和姿态跟踪的联合学习方法(2019/01-2021/12)

   国家自然科学基金中德国际合作项目(主持) 

• 抗遮挡的行人检测算法研究(2018/01-2020/12)

   国家自然科学基金青年项目(主持)   

• 城市交通场景中的遮挡行人检测算法研究(2018/07-2021/07)

   江苏省自然科学基金面上项目(主持)

• 基于深度学习的视频中人体分析技术(2018/09-2019/09)

   CCF-腾讯犀牛鸟基金项目(主持)

• 基于深度学习的海上目标检测算法研究(2018/04-2020/04)

  南京理工大学自主科研专项计划项目(主持)

• 面向无人驾驶的高精度行人检测系统(2014/09至今)

  德国马普所、日本丰田汽车公司国际合作项目(核心骨干)

• 面向无人车的全景彩色立体红外相机构建及其在越野环境感知和自主定位中的应用研究(2017/01-2020/12)

  国家自然科学基金面上项目(参与,排名第二)

• 基于无人车和微型无人机的野外道路检测和追踪(2015.07-2018.06)

  江苏省自然科学基金面上项目(参与,排名第二)

发表论文

近年来代表性论文:

• Yunan Liu, Chunpeng Wang*, Mingyu Lu, Jian Yang, Jie Gui, Shanshan Zhang*. From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024. (CCF-A类期刊)

• Yanling Tian, Di Chen, Yunan Liu, Jian Yang, Shanshan Zhang*. Divide and Conquer: Hybrid Pre-training for Person Search. AAAI Conference on Artificial Intelligence (AAAI), 2024. (CCF-A类会议)

• Jie Xu, Shanshan Zhang*, Jian Yang. Adaptive Decoupled Pose Knowledge Distillation. ACM Multimedia (MM), 2023. (CCF-A类会议)

• Shenjian Gong, Jian Yang, Shanshan Zhang*. Adaptive Teaching for Cross-Domain Crowd Counting. IEEE Transactions on Multimedia (T-MM), 2023. (CCF-B类期刊)

• Mingqian Ji, Jian Yang, Shanshan Zhang*. OKGR: Occluded Keypoint Generation and Refinement for 3D Object Detection. Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2023. (CCF-C类会议,最佳学生论文)

• Gang Li, Xiang Li*, Yujie Wang, Yichao Wu, Ding Liang, Shanshan Zhang*. DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection. Annual Conference on Neural Information Processing Systems (NeurIPS), 2022. (CCF-A类会议)

• Shenjian Gong, Shanshan Zhang*, Jian Yang, Dengxin Dai, Bernt Schiele. Bi-level Alignment for Cross-Domain Crowd Counting. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (CCF-A类会议)

• Andreas Doering#, Di Chen#Shanshan Zhang, Bernt Schiele, Jürgen Gall. PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (CCF-A类会议)

• Gang Li, Xiang Li*, Yujie Wang, Yichao Wu, Ding Liang, Shanshan Zhang*. PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection. European Conference on Computer Vision (ECCV), 2022. (计算机视觉顶级会议)

• Shenjian Gong, Shanshan Zhang*, Jian Yang, Dengxin Dai, Bernt Schiele. Class-Agnostic Object Counting Robust to Intraclass Diversity. European Conference on Computer Vision (ECCV), 2022. (计算机视觉顶级会议)

• Di Chen#, Andreas Doering#Shanshan Zhang*, Jian Yang*, Jürgen Gall, Bernt Schiele. Keypoint Message Passing for Video-based Person Re-Identification. AAAI Conference on Artificial Intelligence (AAAI), 2022. (CCF-A类会议)

• Gang Li#, Xiang Li#, Yujie Wang, Shanshan Zhang*, Yichao Wu, Ding Liang. Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation. AAAI Conference on Artificial Intelligence (AAAI), 2022. (CCF-A类会议)

• Yanling Tian, Di Chen, Yunan Liu, Shanshan Zhang*, Jian Yang. Grouped Adaptive Loss Weighting for Person Search. ACM International Conference on Multimedia (MM), 2022. (CCF-A类会议)

• Shanshan Zhang, Di Chen, Jian Yang*, Bernt Schiele. Guided Attention in CNNs for Occluded Pedestrian Detection and Re-identification. International Journal of Computer Vision (IJCV), 129(6):1875-1892, 2021. (CCF-A类期刊)

• Di Chen, Shanshan Zhang*, Jian Yang*, Bernt Schiele. Norm-Aware Embedding for Efficient Person Search and Tracking. International Journal of Computer Vision (IJCV), 129(9), 3154–3168, 2021. (CCF-A类期刊)

• Yunan Liu, Shanshan Zhang*, Jie Xu, Jian Yang and Yu-Wing Tai. An Accurate and Lightweight Method for Human Body Image Super-Resolution. IEEE Transactions on Image Processing (T-IP), 30(2): 2888 - 2897, 2021. (CCF-A类期刊)

• Yunan Liu, Shanshan Zhang*, Yang Li, Jian Yang. Learning to Adapt via Latent Domains for Adaptive Semantic Segmentation. Annual Conference on Neural Information Processing Systems (NeurIPS), 2021. (CCF-A类会议)

• Farzaneh Rezaeianaran, Rakshith Shetty, Rahaf Aljundi, Daniel Olmeda Reino, Shanshan Zhang, Bernt Schiele. Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection. International Conference on Computer Vision (ICCV), 2021. (CCF-A类会议)

• Yunan Liu, Shanshan Zhang*, Jian Yang, Pong Chi Yuen. Hierarchical Information Passing Based Noise-Tolerant Hybrid Learning for Semi-Supervised Human Parsing. AAAI Conference on Artificial Intelligence (AAAI), 2021. (CCF-A类会议)

• Mengyuan Ding, Shanshan Zhang*, Jian Yang. Improving Pedestrian Detection from a Long-tailed Domain Perspective. ACM Multimedia (MM), 2021. (CCF-A类会议, Oral)

• Di Chen, Shanshan Zhang*, Wanli Ouyang, Jian Yang*, Ying Tai. Person Search by Separated Modeling and A Mask-Guided Two-Stream CNN Model. IEEE Transactions on Image Processing (T-IP). 29(2): 4669-4682, 2020. (CCF-A类期刊)

• Di Chen, Shanshan Zhang*, Jian Yang*, Bernt Schiele. Norm-Aware Embedding for Efficient Person Search. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2020. (CCF-A类会议)

• Shanshan Zhang, Rodrigo Benenson, Mohamed Omran, Jan Hosang, Bernt Schiele. Towards Reaching Human Performance in Pedestrian Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 40(4): 973-986,2018. (CCF-A类期刊)

• Shanshan Zhang, Jian Yang, Bernt Schiele. Occluded Pedestrian Detection through Guide Attention in CNNs. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, 2018. (CCF-A类会议)

• Shanshan Zhang, Rodrigo Benenson, Bernt Schiele. CityPersons: A Diverse Dataset for Pedestrian Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, USA, 2017. (CCF-A类会议, Spotlight)

• Shanshan Zhang, Rodrigo Benenson, Mohamed Omran, Jan Hosang, Bernt Schiele. How Far are We from Solving Pedestrian Detection? IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, USA, 2016. (CCF-A类会议)

• Shanshan Zhang, Rodrigo Benenson, Bernt Schiele. Filtered Channel Features for Pedestrian Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, USA, 2015. (CCF-A类会议)

• Shanshan Zhang, Christian Bauckhage, Armin B. Cremers. Informed Haar-like Features Improve Pedestrian Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, USA, 2014. (CCF-A类会议)

• Di Chen, Shanshan Zhang*, Wanli Ouyang, Jian Yang*, Ying Tai. Person Search via A Mask-guided Two-stream CNN Model. European Conference on Computer Vision (ECCV), Munich, Germany, 2018. (计算机视觉顶级会议)

• Di Chen, Shanshan Zhang*, Wanli Ouyang, Jian Yang*, Bernt Schiele. Hierarchical Online Instance Matching for Person Search. AAAI Conference on Artificial Intelligence (AAAI), New York City, USA, 2020. (CCF-A类会议, Oral)

指导学生情况

目前指导博士生7名,硕士生6名,本科生若干名。

欢迎有较好的数学、英语基础和较强编程能力,且对计算机视觉、深度学习、无人驾驶等领域感兴趣的同学与我联系。