计算机视觉、人工智能、模式识别

多媒体内容生成与伪造检测、自动驾驶、人脸识别、智能视频分析

人工智能基础理论、AI for Science

081104-模式识别与智能系统

计算机视觉

2013-09--2016-07   中国科学院自动化研究所   工学博士
2010-09--2013-04   西安电子科技大学   工学硕士
2005-09--2009-07   西安电子科技大学   工学学士

   

2020-10~现在, 中国科学院自动化研究所, 副研究员
2016-07~2020-09,中国科学院自动化研究所, 助理研究员

2019-11-08-今,中国图象图形学会机器视觉专委会, 委员

（1） 2020 Neural Networks 最佳论文奖, 一等奖, 其他, 2023
（2） 中国图象图形学学会自然科学奖, 二等奖, 其他, 2022
（3） "根尖智能杯"大规模行人检索竞赛, 一等奖, 其他, 2020

[1] 雷震, 杨阳, 翁敦芳. 基于属性定位与关联的行人属性识别方法及系统. CN: CN113239820B, 2023-06-27.
[2] 杨阳, 雷震. 基于像素和特征转移相融合的无监督行人再识别方法. CN112347995B, 2022-09-23.
[3] 雷震, 杨阳, 陶建华, 翁敦芳. 基于Transformer的标记选择和合并的表情识别方法及系统. CN: CN113705541A, 2021-11-26.
[4] 雷震, 杨阳, 翁敦芳. 基于注意力机制的行人属性识别方法、系统、装置. CN: CN112434683A, 2021-03-02.

   

[1] Tan, Zichang, Zhang, Guiwei, Tan, Zihui, Tiwari, Prayag, Wang, Yi, Yang, Yang. CAM2Former: Fusion of Camera-specific Class Activation Map matters for occluded person re-identification. INFORMATION FUSION[J]. 2025, 第 6 作者  通讯作者  120: 103011, http://dx.doi.org/10.1016/j.inffus.2025.103011.
[2] Benzhi Wang, Jingkai Zhou, Jingqi Bai, 杨阳, Weihua Chen, Fan Wang, 雷震. RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images. AAAI. 2025, 第 4 作者null(null): 
[3] Jingqi Bai, Jingkai Zhou, Benzhi Wang, Weihua Chen, 杨阳, 雷震, Fan Wang. Layer-Animate for Transparent Video Generation. ICASSP. 2025, 第 5 作者null(null): 
[4] Yiheng Li, 杨阳, Zichang Tan, Huan Liu, Weihua Chen, Xu Zhou, 雷震. Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation. CVPR. 2025, 第 2 作者null(null): 
[5] 李毅恒, 杨阳, 雷震. RCTrans: Radar-Camera Transformer via Radar Densifier and Sequential Decoder for 3D Object Detection. AAAI Conference on Artificail Intelligence (AAAI). 2025, 第 2 作者null(null): 
[6] Li, Yiheng, Yang, Yang, Lei, Zhen. CoreNet: Conflict Resolution Network for point-pixel misalignment and sub-task suppression of 3D LiDAR-camera object detection. INFORMATION FUSION[J]. 2025, 第 2 作者118: 102896, http://dx.doi.org/10.1016/j.inffus.2024.102896.
[7] Xingye Fang, Yang Yang, Ying Fu. Visible-Infrared Person Re-Identification via Semantic Alignment and Affinity Inference. International Conference on Computer Vision (ICCV). 2023, 第 2 作者
[8] Benzhi Wang, Yang Yang, Jinlin Wu, Guo-Jun Qi, Zhen Lei. Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search. International Conference on Computer Vision (ICCV). 2023, 第 2 作者
[9] Jinlin Wu, Lingxiao He, Wu Liu, Yang Yang, Zhen Lei, Tao Mei, Stan Z. Li. CAViT: Contextual Alignment Vision Transformer for Video Object Re-identification. European Conference on Computer Vision (ECCV). 2022, 第 4 作者
[10] Yang, Yang, Tan, Zichang, Tiwari, Prayag, Pandey, Hari Mohan, Wan, Jun, Lei, Zhen, Guo, Guodong, Li, Stan Z. Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition. INTERNATIONAL JOURNAL OF COMPUTER VISION[J]. 2021, 第 1 作者129(10): 2731-2744, http://dx.doi.org/10.1007/s11263-021-01499-z.
[11] Yang, Yang, Wang, Guanan, Tiwari, Prayag, Pandey, Hari Mohan, Lei, Zhen. Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Reidentification. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS[J]. 2021, 第 1 作者http://dx.doi.org/10.1109/TNNLS.2021.3128269.
[12] Wang, Guanan, Yang, Shuo, Liu, Huanyu, Wang, Zhicheng, Yang, Yang, Wang, Shuliang, Yu, Gang, Zhou, Erjin, Sun, Jian, IEEE. High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR). 2020, 第 5 作者6448-6457, http://dx.doi.org/10.1109/CVPR42600.2020.00648.
[13] Wang, Guanan, Yang, Yang, Zhang, Tianzhu, Cheng, Jian, Hou, Zengguang, Tiwari, Prayag, Pandey, Hari Mohan. Cross-modality paired-images generation and augmentation for RGB-infrared person re-identification. NEURAL NETWORKS[J]. 2020, 第 2 作者128: 294-304, http://dx.doi.org/10.1016/j.neunet.2020.05.008.
[14] Wu, Jinlin, Yang, Yang, Lei, Zhen, Wang, Jinqiao, Li, Stan Z, Tiwari, Prayag, Pandey, Hari Mohan. An end-to-end exemplar association for unsupervised person Re-identification. NEURAL NETWORKS[J]. 2020, 第 2 作者129: 43-54, http://dx.doi.org/10.1016/j.neunet.2020.05.015.
[15] Wu, Jinlin, Yang, Yang, Liu, Hao, Liao, Shengcai, Lei, Zhen, Li, Stan Z, IEEE. Unsupervised Graph Association for Person Re-identification. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019). 2019, 第 2 作者8320-8329, http://dx.doi.org/10.1109/ICCV.2019.00841.
[16] Tan, Zichang, Yang, Yang, Wan, Jun, Hang, Hanyuan, Guo, Guodong, Li, Stan Z. Attention-Based Pedestrian Attribute Analysis. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2019, 第 2 作者28(12): 6126-6140, http://dx.doi.org/10.1109/TIP.2019.2919199.
[17] Wang, Guanan, Zhang, Tianzhu, Cheng, Jian, Liu, Si, Yang, Yang, Hou, Zengguang, IEEE. RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019). 2019, 第 5 作者3622-3631, http://dx.doi.org/10.1109/ICCV.2019.00372.
[18] Wu, Jinlin, Liao, Shengcai, Lei, Zhen, Wang, Xiaobo, Yang, Yang, Li, Stan Z, IEEE. Clustering and Dynamic Sampling Based Unsupervised Domain Adaptation for Person Re-Identification. IEEE International Conference on Multimedia and Expo (ICME). 2019, 第 5 作者  通讯作者  886-891, 
[19] Hongsheng Wang, Shengcai Liao, Zhen Lei, Yang Yang. Is Re-ranking Useful for Open-set Person Re-identification?. IEEE International Conference on Big Data (Big Data). 2018, 第 4 作者2018: 4625-4631, 
[20] Wang, Xiaobo, Lei, Zhen, Liao, Shengcai, Guo, Xiaojie, Yang, Yang, Li, Stan Z. Dependence-Aware Feature Coding for Person Re-Identification. IEEE SIGNAL PROCESSING LETTERS[J]. 2018, 第 5 作者25(4): 506-510, http://dx.doi.org/10.1109/LSP.2018.2803776.
[21] Yang Yang, Wen Longyin, Lyu Siwei, Li Stan Z, AAAI. Unsupervised Learning of Multi-Level Descriptors for Person Re-Identification. THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE. 2017, 第 1 作者  通讯作者  4306-4312, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485630704050.
[22] Cheng Da, Yang Yang, Kun Ding, Chunlei Huo, Shiming Xiang, Chunhong Pan. EFFICIENT SIMILARITY LEARNING FOR ASYMMETRIC HASHING. IEEE International Conference on Image Processing. 2017, 第 2 作者http://ir.ia.ac.cn/handle/173211/15384.
[23] 杨阳, 文珑银, 李子青, LyuSiwei. Unsupervised Learning of Multi-Level Descriptors for Person Re-Identification. AAAI Conference on Artificial Intelligence. 2017, 第 1 作者http://ir.ia.ac.cn/handle/173211/19793.
[24] Yang Yang, Lei Zhen, Zhang Shifeng, Shi Hailin, Li Stan Z, AAAI. Metric Embedded Discriminative Vocabulary Learning for High-Level Person Representation. THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE. 2016, 第 1 作者  通讯作者  3648-3654, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485474203094.
[25] Yang Yang, Liao Shengcai, Lei Zhen, Li Stan Z, AAAI. Large Scale Similarity Learning Using Similar Pairs for Person Verification. THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE. 2016, 第 1 作者  通讯作者  3655-3661, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485474203095.
[26] Shi, Hailin, Yang, Yang, Zhu, Xiangyu, Liao, Shengcai, Lei, Zhen, Zheng, Weishi, Li, Stan Z, Leibe, B, Matas, J, Sebe, N, Welling, M. Embedding Deep Metric for Person Re-identification: A Study Against Large Variations. COMPUTER VISION - ECCV 2016, PT I. 2016, 第 2 作者9905: 732-748, 
[27] Shengcai Liao, Yang Yang, Zhen Lei. Color Models and Weighted Covariance Estimation for Person Re-Identification. International Conference on Pattern Recognition, (ICPR2014).. 2014, 第 2 作者1874 - 1879, http://ir.ia.ac.cn/handle/173211/4462.
[28] Lei Zhen, Yang Yang, Li Stan Z. Stacked Deformable Part Model with Shape Regression for Object Part Localization. COMPUTER VISION - ECCV 2014, PT II. 2014, 第 2 作者568-583, http://ir.ia.ac.cn/handle/173211/4450.
[29] Zhang Xiangrong, Yang Yang, Jia Hanghua, Zhou Huiyu, Jiao Licheng, IEEE. Low-rank Representation Based Action Recognition. PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN). 2014, 第 2 作者1812-1818, 
[30] Yang Yang, Yang Jimei, Yan Junjie, Liao Shengcai, Yi Dong, Li Stan Z, Fleet D, Pajdla T, Schiele B, Tuytelaars T. Salient Color Names for Person Re-identification. COMPUTER VISION - ECCV 2014, PT I. 2014, 第 1 作者8689: 536-551, 
[31] Zhang, Xiangrong, Yang, Yang, Jiao, L C, Dong, Feng. Manifold-constrained coding and sparse representation for human action recognition. PATTERN RECOGNITION[J]. 2013, 第 2 作者46(7): 1819-1831, http://dx.doi.org/10.1016/j.patcog.2012.10.011.

   

（ 1 ） 跨场景的行人关联方法研究, 负责人, 国家任务, 2019-01--2021-12
（ 2 ） 智能化全天候多场景视力障碍训练与视觉增强技术及产品的研发, 参与, 国家任务, 2020-07--2023-06
（ 3 ） 通用视觉模型关键技术研究, 参与, 国家任务, 2021-12--2024-11

（1）讲习班：行人再识别的表示学习   欧洲计算机视觉国际会议   2018-09-08
（2）讲习班：行人再识别研究现状和未来   国际模式识别大会   2018-08-20
（3）讲习班：行人再辨识研究进展   计算机视觉领域盛会   2017-10-12