Prof. Qixiang Ye 

Address: University of Chinese Academy of Sciences, A-2 BLDG, RM.457,  Huairou District, Beijing, China, 101408.

Co-Funding Pri-SDL with Prof. Jianbin Jiao & Zhenjun Han

Email: qxye at ucas dot ac dot cn  ScholarPage 

Phon: 86-10-69671881

General Info

Qixiang Ye is a full professor with the University of Chinese Academy of Sciences since 2016. He is one of the funding directors of pattern recognition and intelligent system development (Pri-SDL) lab. He received the B.S. and M.S. degrees in mechanical and electrical engineering from Harbin Institute of Technology, China, respectively, and the Ph.D. degree from the Institute of Computing Technology, Chinese Academy of Sciences. He was a visiting assistant professor with the Institute of Advanced Computer Studies (UMIACS), University of Maryland, College Park until 2013 and a visiting scholar of Duke University EECS in 2016. His research interests include visual object detection and machine learning, especially for feature representation learning, weakly supervised learning, self-supervised learning for visual object sensing. With more than 180 papers published in refereed conferences and journals including IEEE T-ITS, TIP, TNN, T-PAMI, CVPR, ICCV, ECCV, AAAI, and NeurIPS. Dr. Ye received the Sony Outstanding Paper Award and the LuJiaXi Young Researcher Award. He is an SPC of IJCAI 2020 and 2021 and on the editor board of IEEE Transactions on Intelligent Transportation System and IEEE Transactions on Circuit and System on Video Technology.


Mar. 2022, Dynamic Support Network paper accepted by TPAMI. Con! [Bob]

Mar. 2022, Self-supervised Motion Perception paper accepted by TNNLS. Con! [Chang]

Jan. 2022, Convex-Hull paper accepted by T-CSVT. Con! [Zonghao]

July. 2021, Three Papers Accepted by ICCV2021, Con! [Yi, Zhiliang, Wei]!

!July. 2021, Long-tailed Distribution Adaptatoin Accepted by ACMMM2021, Con![Zhiliang]!

Mar. 2021, Five Papers Accepted by CVPR 2021, Con![Binghao, Tianning, Zonghao, Bohao, Yuchao]

Feb. 2021, Harmonic Feature Activation (HFA) for few-shot learning is accepted by TIP. Con! [Binghao]

Jan. 2021, FreeAnchor is accepted by T-PAMI. Con! [Xiaosong]

Dec. 2020, Two papers are accepted by AAAI2020 [Con! Fang, and Mengying]

Nov. 2020, A ToolBox for general image-to-mask tasks SDL-Skeleton is released. [Code]

Oct. 2020, Fang Wan Recieved 100 Outstanding Ph.D thesis, CAS, [Con! Fang]

Aug. 2020, IJCAI 2021, Senior Programm Committee (SPC) Member

Aug. 2020, Anual Progress Review at Valse 2020 [slides]

Jul. 2020: Four papers are accepted by ECCV 2020. Con![Boyu, Pengxu, Xinshuan, Yunpeng] 

Apr. 2020:  SRN(Side-Output Residual Network [source_code])Accepted by IEEE TNNLS,Con! WeiKe

Mar. 2020: To be NeurIPS, ECCV 2020 Program Committee Member.

Mar. 2020: Five papers are accepted by CVPR 2020. Con![WeiKe,Chang,YiYaoYuan, Yunpeng] 

Nov. 2019: Two papers are accepted by AAAI 2020, SPSTracker achieves highest EAO. Con! [Chang, Qintao]

Oct. 2019: To be IJCAI2020 Senior Programm Committee (SPC) Member

Sep. 2019: Two papers are accepted by NeurIPS 2019, FreeAnchor-Best One-stage Detector. Con! [Xiaosong and HuJie]

Jul. 2019: Two papers are accepted by ICCV 2019, Con! [Yao Ding and Haolan]

Jun. 2019: We won the CVPR 2019 SkelNetOn 2019, Con! [Chang]

Mar.2019: A Large-scale Security Inspection X-ray Benchmark (SixRay) released. CVPR2019 paper [pdf]  [iFeng News] [Con! CaiJing].

Feb.2019: Five Papers accepted to IEEE CVPR 2019 [Con! Fang,  Yi, Chang, and CaiJing].

Feb.2019: Weakly Supervised Object Detection, Localization, and Instance Segmentation: A Tutorial at Valse Seminar [TalkSlides]
Jan.2019: Min-entropy Latent Model for Weakly Supervised Object Detection Accepted by PAMI [Con! Fang][paper][torch-code][pytorch-code]
Dec.2018: Outstanding Researcher of Younth Innovation Promotion Association,  Chinese Academy of Sciences [News]
Jun.2018:  Invited Talk about Side-residual Network and Linear Span Network at SumSung Research [Slides-Paper-Code]
Mar.2018: Three Papers accepted At IEEE CVPR 2018, inlcuding a spotlight paper [Con!Yanzhao, Weijian, Fang].
Mar.2018: Wei Ke, my first PH.D student, was hornored CAS President Award [Link]
Sep.2017: Winner of first Aerial Object Detection Competition [Con! Yanzhao, Weijian, Fanand Yi] [News]
Mar.2017: Winer of ICCV 2017 Symmetry Detection Competition [Link]
Mar.2017: Three Papers accepted At IEEE CVPR 2017, , inlcuding an Oral paper [Con! WeiKe,Yanzhao] [News]
Jun. 2016: Invited Talk about Text Detection and Recognition[PAMI Survey Paper]
May.2015: Natural Science Award from Chinese Institute of Electronics.
May.2014: Young Researcher Promotion Project of Chinese Academy of Sciences [News]


1. Bachelor and Master of science, Harbin Institute of Technology, China
2. Ph.D in computer science, Institute of Computing Technology, Chinese Academy of Sciences
3. Visiting Assitant Professor of University of Maryland, College Park
4. Visiting Scholar of Electrical and Computer Engineering, Duke 
5. Full Professor of University of Chinese Academy of Sciences


PH.D and Masters

1.  Yuan Yao              Ph.D  student since fall 2017. Research Areas:  Self-supervised Feature Learning

2.  Xiaosong Zhang     Ph.D  student since fall 2018. Research Areas:  Visual Object Detection

3.  Boyu Yang            Ph. D student since fall 2018. Research Areas: Few-shot Incremental Learning 

4.  Binghao Liu          Ph. D student since Spring 2018. Research Areas: Few-shot Incremental Learning 

5. Zhiliang Peng       Ph. D student since fall 2019. Research Areas: Self-supervised Feature Learning

6.  Zonghao Guo       Ph. D student since fall 2019. Research Areas: Visual  Object Detection

7.  Mengying Fu         Ph.D  student since fall 2019. Research Areas:  Active Learning for Detection

8. Feng Liu               Master student since fall 2020. Research Areas:  Active Learning for Detection

9. Mingxiang Liao   Master student since fall 2020. Research Areas:  Weakly Supervised Object Detection

10. Bohao Li              Master student since fall 2020. Research Areas:  Few-shot Object Detection

11. Xuran Lu             Master student since fall 2021. Research Areas:  Visual Object Detection

12. Hongtian Yu         Master student since fall 2021. Research Areas:  Visual Object Detection

13. Xiaozhong Chen  Master student since fall 2021. Research Areas:  Few-shot Object Detection


1. Bo Wu                (2011)  Master , Visual Object Detection, Agricalture Bank of China
2. Dongsheng Yu   (2011)   Master, , Visual Object Detection,  Tecent
3. Jixiang Liang      (2013)  Master, Visual Object Detection, Agricalture Bank of China  (Hornored Natinal Scholarship 2012) 
4. Yaozhang           (2015)  Master, Visual Object Detection,   China Aerospace Science and Industrial Corporation
5. Yanting Cui         (2015)  Master, Visual Object Detection,  Alibaba
6. Xiansong Huang (2017)  Master, Visual Object Detection, Ctrip
7. Yanran  Liu         (2017)  Master, Visual Object Detection,  Datang Telecom
8. Wei Ke                (2018)  Ph. D , Object and Symmetry Detection, Carnegie Mellon University,  (Hornored Natinal Scholarship, CAS President Scholarship 2017) 

9. Caijing Miao         (2019) Master, Weakly Supervised Object Detection, KingSoft

10. Fang Wan          (2019)  Ph. D, Weakly Supervised Object Detection, UCAS

11. Haolan Xue        (2020) Master, Weakly Supervised Object Detection, Alibaba DAMO

12. Tianliang Zhang (2020) Ph. D,  Visual Object Detection, Tecent,  (Hornored Natinal Scholarship 2020) 

13. Chang Liu           (2021)  Ph. D,  Self-supervised Learning, Tsinghua University(Hornored Natinal Scholarship 2020) 

14. Wei Gao              (2021) Master, Weakly Supervised Object Detection, Alibaba

15.  Tianing Yuan      (2022)Master, Active Object Detection, Huawei

16. Yunxiao Zhang    (2022)Master,  Few-shot Incremental Learning

17. Zixiang Zhong    (2022)Master,  Few-shot Incremental Learning

18. Jinge Ma             (2021) Bachelor, Visual Object Detection,  University of Michigan, USA     

19. Tianren Ma        (2022) Bachelor, Visual Object Detection,    UCAS

20. Yumeng Zhang  (2022) Bachelor,  Johns Hopkins University, USA

Honors & Distinctions

1.Outstanding Researcher of Youth Innovation Promotion Association, Chinese Academy of Sciences, 2018. 

2."LuJiaXi" Outstanding Young Researcher Awards, 2014
3.Top-10 most Cited Papers in The Past Five Years of Image and Vision Computing, 2010
4.Outstanding Course of Chinese Academy of Sciences, 2007 and 2009
5.CAS-Sony Outstanding Paper Award 2005
6.Scholarship of Institute of Computing Technology, Chinese Academy of Sciences, 2005


Object Detection (new)

[1] X. Zhang, F. Wan, C. Liu, X. Ji, Q. Ye, "Learning to Match Anchors for Visual Object Detection," IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI), 44(6):3096 - 3109, 2022. [pdf][source-code].

[2] B. Yang, M. Lin, Z. Zhang, B. Liu, X. Liang, R. Ji, Q. Ye, "Dynamic Support Network for Few-shot Incremental Learning," IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI), DOI:10.1109/TPAMI.2022.3175849. [pdf][source-code].

[3] Z. G, X. Zhang, C. Liu, J. Jiao, X. Ji, Q. Ye, "Convex-Hull Feature Adaptation for Oriented and Densely Packed Object Detection," IEEE Trans. Circuits Syst. Video Technol. (T-CSVT), DOI: 10.1109/TCSVT.2022.3140248. [pdf][source_code].

[4] C. Liu, Y. Tian  J. Jiao,  Q. Ye, "Adaptive Linear Span Network for Object Skeleton Detection," IEEE Trans. Image Process. (TIP) 2021, 30:5096-5108. [pdf][source_code].

[5] Z. Peng, W. Huang, S. Gu, L. Xie, Y. Wang, J. Jiao, Q. Ye, Conformer: Local Features Coupling Global Representations for Visual Recognition, ICCV 2021. [pdf][code]

[6] T. Yuan, F. Wan, M. Fu, J. Liu, C. Xu, X. Ji, Q. Ye, "Multiple Instance Active Learning for Object Detection," IEEE CVPR 2021[pdf][source_code].

[7] Z. Guo, C. Liu, X. Zhang, J. Jiao, X. Ji, Q. Ye, "Beyond Bounding-Box: Convex-hull Feature Adaptation for Oriented and Densely Packed Object Detection," IEEE CVPR 2021 [pdf][source_code].

[8] B. Li, B. Yang, C. Liu, F. Liu, R. Ji, Q. Ye, "Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection," IEEE CVPR 2021 [pdf][source_code].

[9] B. Liu, Y. Ding, J. Jiao, X. Ji, Q. Ye, "Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation," IEEE CVPR 2021[pdf][source_code].

[10] B. Liu, J. Jiao, Q. Ye, "Harmonic Feature Activation for Few-Shot Semantic Segmentation," IEEE Trans. Image Process. (TIP), 30(2):3142 - 3153, 2021 [pdf][source_code].

[11] W. Ke, J. Chen, J. Jiao, G. Zhao, Q. Ye, "SRN: Side-output Residual Network for Object Reflection Symmetry Detection and Beyond," IEEE Trans. Neural Networks Learn. Syst. (TNNLS), 32(5):1881-1895, 2021. [pdf][source_code]

[12] W. Ke, T. Zhang, Z. Huang, Dong Huang, Q. Ye, "Multiple Anchor Learning for  Visual Object Detection, " IEEE CVPR, 2020[pdf][source_code]

[13] M. Lin, Y. X. Tian, B. Zhang, Q. Ye,  W. Liu, D. Doermann, "iffDetector: Inference-Aware Feature Filtering for Object Detection," IEEE Trans. Neural Networks Learn. Syst. (TNNLS), 2021 (To Appear).

[14] F. Liu, X. Zhang, F. Wan, X. Ji, Q. Ye, "Domain Contrast for Domain Adaptive Object Detection,"  IEEE Trans. Circuits Syst. Video Technol. (T-CSVT)2021 (To Appear).

[15] J. H, L. Zhou, X. Wang, J. Zhang, Y. Mao, Q. Ye, "SPSTracter: Sub-Peak Depression of Response Map for Robust Object Tracking," AAAI 2020. [pdf][source-code]

[16] B. Yang, C Liu, B. Li, J. Jiao,  Q. Ye, "Prototype Mixture Models for Few-shot Semantic Segmentation," ECCV 2020. [pdf][source-code].

[17] Y. Zhu, X. Liang, B. Lin, J. Jiao, Q. Ye, L. Lin, X. Liang, "Configurable Graph Reasoning for Visual Relationship Detection,"  IEEE Trans. Neural Networks Learn. Syst. (TNNLS), 2020. [pdf]

[18] Y. Cai, C. Liu,  P. Cheng, D. Du, Bo. Li, W. Wang, Q. Ye,  "Scale-residual Learning Network for Scene Text Detection, "  IEEE Trans. Circuits Syst. Video Technol. (T-CSVT)2021:31(7):2725-2738. [pdf]

[19] T. Zhang, Q. Ye, B. Zhang,  J. Liu, X. Zhang, Q. Tian,  "Feature Calibration Network for Occluded Pedestrian Detection, " IEEE Trans. Intell. Transp. Syst. (T-ITS)2021[PDF].

[20] X. Zhang, F. Wan, C. Liu, R. Ji, Q. Ye, "FreeAnchor: Learning to Match Anchors for Visual Object Detection," NeurIPS 2019. [pdf][source-code]

Weakly Supervised & Self-Learning 

[21] W. Gao, F. Wan, etc., B. Zhou, Q. Ye,TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization, ICCV 2021. [pdf][code]

[22Q. Ye, F. Wan, C. Liu, Q. Huang, X. Ji,  "Continuation Multiple Instance Learning for Weakly and Fully Supervised Object Detection, "  IEEE Trans. Neural Networks Learn. Syst. (TNNLS),10.1109/TNNLS.2021.3070801 . [pdf][source_code]

[23] Z. Peng, W. Huang, Z. Guo, X. Zhang, J. Jiao, Q. Ye, "Long-tailed Distribution Adaptation," ACM MM, 2021. [pdf][source_code]

[24] B. Yang, F. Wan, B. Li, C. Liu, X. Ji, Q. Ye, "Part-based Semantic Transform for Few-shot Semantic Segmentation,"  IEEE Trans. Neural Networks Learn. Syst. (TNNLS) , 2021, 10.1109/TNNLS.2021.3084252. [pdf][source_code]

[25] C. Zhang, Z. Li, J. Liu, P. Peng, Q.  Ye, S.  Lu, T.  Huang, Y.  Tian,  "Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection",  IEEE Transactions on Multimedia 10.1109/TMM.2021.3078141 [pdf]

[26]  F. Wan, T. Yuan, M. Fu, Q. Huang, X. Ji, Q. Ye, "Nearest Neighbor Classifier Embedded Network for Active Learning," AAAI 2021 [pdf].

[27]  M. Fu, T. Yuan, F. Wang, S. Xu, Q. Ye, "Agreement-Discrepancy-Selection: Active Learning with Progressive Distribution Alignment," AAAI 2021 [pdf].

[28] K. Sun, H. Liu, Q. Ye,  Y. Gao, J. Liu, L. Shao, R. Ji, "Domain General Face Forgery Detection by Learning to Weight," AAAI 2021 [pdf].

[29] Y. Yao, C. Liu, D. Luo, Y. Zhou, Q. Ye, "Video Playback Rate Perception for Self-Supervised Spatio-Temporal RepresenationLearning," IEEE CVPR, 2020. [pdf][source-code]. 

[30] Y. Zhai, S. Lv, Q. Ye, J. Chen, R. Ji, Y. Tian, "AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification," IEEE CVPR, 2020. [pdf]

[31] D. Luo, C. Liu, Y. Zhou, W. Wang, Q. Ye., Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning, AAAI 2020. [pdf][source-code]

[32] H. Xue, C. Liu, F. Wan, J. Jiao, Q. Ye, "DANet: Divergent Activation for Weakly Supervised Object Localization," IEEE ICCV 2019. [pdf] [source-code]

[33] F. Wan, C. Liu, X. Ji, J. Jiao, Q. Ye, "CMIL: Continuation Multiple Instance Learning for Weakly Supervised object Detection," IEEE CVPR, 2019 (Oral). [pdf][source-code][Caffe+ResNet]

[34] Y. Zhu, Y. Zhou, H. Xu, Q. Ye, D. Doeramann, J. Jiao, "Learning Instance Activation Maps for Weakly Supervised Instance Segmentation," IEEE CVPR, 2019 [pdf].

[35] C. Miao, X. Xie, F. Wang, C. Su, J. Jiao, Q. Ye, "SIXray: A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images," IEEE CVPR, 2019 [pdf][dataset&code]

[36] F. Wan, P. Wei, Z. Han, J. Jiao, Q. Ye, “Min-entropy Latent Model for Weakly Supervised object Detection,” IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI), 41(10): 2395-2409 (2019). [IEEE PAMI PDF][Arxiv PDF][Code][pytorch-code]

[37] F. Wan, P. Wei, Z. Han, J. Jiao, Q. Ye, “Min-entropy Latent Model for Weakly Supervised object Detection,” IEEE CVPR, 2018: 1297-1306. [pdf]-[source code]-[bibtex]

[38] Y. Zhou, Y. Zhu, Q. Ye, Q. Qiu, J. Jiao, “Weakly Supervised Instance Segmentation using Class Peak Response,” IEEE CVPR, 2018 (Spotlight). [pdf]-[source code]-[bibtex]

[39] W. Deng, L. Zheng, Q. Ye, J. Jiao, “Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification,” IEEE CVPR, 2018.  [pdf]-[source code]-[bibtex]

[40Q. Ye, T. Zhang, Q. Qiu, B. Zhang, J. Chen, and G. Sapiro, "Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model," IEEE CVPR, 2017. [pdf]-[source code]-[bibtex]

[41] Y. Zhu, Y. Zhou, Q. Ye, Q. Qiu, and J. Jiao, "Soft Proposal Network for Weakly Supervised Object Localization," IEEE ICCV, 2017. [pdf]-[source code]-[bibtex]

Feature Learning

[42] C. Liu, Y. Yao, D. Luo, Y. Zhou, Q. Ye, "Self-supervised Motion Perception for Spatio-temporal Representation Learning,"  IEEE Trans. Neural Networks Learn. Syst. (TNNLS), 2022.[source-code].

[43] X. Zheng, R.  Ji, Y.  Chen, Q. Wang, B. Zhang, Q. Ye, J. Chen, F.  Huang, Y.  Tian, MIGO-NAS: Towards Fast and Generalizable Neural Architecture Search, IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI), DOI: 10.1109/TPAMI.2021.3050494. [pdf][source-code].

[44] B Lin, Y Zhu, Y Long, X Liang, Q Ye, L Lin, Retreat for Advancing: Dynamic Reinforced Instruction Attacker for Robust Visual Navigation, IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI), DOI:10.1109/TPAMI.2021.3097435. [pdf]

[45]  M. Lin, L. Cao, S. Li, Q. Ye,  Y. Tian, J. Liu, Q. Tian, R. Ji, "Filter Sketch for Network Pruning,"  IEEE Trans. Neural Networks Learn. Syst. (TNNLS) , 2021.

[46] Y. Tian, C. Liu, L. Xie, J. Jiao, Q.Ye,  Discretization-aware Architecture Search, Pattern Recognition, 2021. [pdf][code]

[47] Y. Ding, Z. Han, Y. Zhou, Y. Zhu, J. Chen, Q. Ye, J. Jiao, Dynamic Perception Framework for Fine-grained Recognition, IEEE Trans. Circuits Syst. Video Technol. (T-CSVT) , To be published.

[48] Y. Li, S. Lin , J. Liu, Q. Ye, M. Wang, F. Yang, J. Ma, Q. Tian, R. Ji, "Towards Compact CNNs via Collaborative Compression," IEEE CVPR 2021.

[49] X. Zheng, R. Ji, Q. Wang, Q. Ye, Q. Tian, "Rethinking Performance Estimation in Neural Architecture Search," IEEE CVPR, 2020 [pdf][source-code].

[50] X. Dong, H. Liu, L. Cao, R. Ji, Q. Ye, Q. Tian, J. Liu, "API-Net: Robust Generative Classifier via a Single Discriminator," ECCV 2020 (To Appear).

[51] Y. Zhai, Q. Ye, S. Lu, M. Jia, R. Ji, Y. Tian,"Multiple Expert Brainstorming for Domain Adaptive Person Re-identification," ECCV 2020 (To Appear).

[52] P. Wei, Z. Xie, H. Lu, Z.  Zhan, Q. Ye, W. Zuo, L. Lin, "Component Divide-and-Conquer for Real-World Image Super-Resolution," ECCV 2020 (To Appear).

[53] L. Zhuo, H. Chen, B. Zhang, Q. Ye, etc., "Cogradient Descent for Bilinear Optimization," IEEE CVPR 2020. [pdf][source_code

[54] J. Hu, R. Ji, S. Zhang, X. Sun, Q. Ye, "Information Competing Process for Learning Diversified Representations," NeurIPS 2019. [pdf]

[55] Y. Ding, Y. Zhou, Y. Zhu, Q. Ye, J. Jiao, "Selective Sparse Sampling for Fine-grained Image Recognition,"  IEEE ICCV, 2019. [pdf][source-code]

[56] C. Liu, F. Wang, Y. Yao, X. Zhang, Q. Ye, "Orthorgnal Decomposition Network For Pixel-wise Binary Classification," IEEE CVPR, 2019. [pdf]

[57] S. Lin, R. Ji, C. Yan, B. Zhang, L. Cao, Q. Ye, F. Huang, D. Doermann, "Towards Optimal Structured CNN Pruning via Generative Adversarial Learning," IEEE CVPR, 2019. [pdf].

[58] L. Zhuo, B. Zhang, C. Chen, Q. Ye, J. Liu, D. Doermann, Calibrated Stochastic Gradient Descent for Convolutional Neural Networks, AAAI 2019.

[59] Z. Li, Z. Han, J. Xing, Q. Ye, X. Yu, J. Jiao, "High performance person re-identification via a boosting ranking ensemble," Pattern Recognition, 94 (10), pp.187-195, 2019. 

[60] C. Liu, W. Ke, F. Qin, Q. Ye, "Linear Span Network for Object Skeleton Detection," ECCV, 2018[pdf]-[source code]-[bibtex]

[61] W. Ke, J. Chen, J. Jiao, and Q. Ye, "SRN: Side-output Residual Network for Object Symmetry Detection in the Wild," IEEE CVPR. (Oral). [pdf]-[source code]-[bibtex]

[62] Y. Zhou, Q. Ye, Q. Qiu, and J. Jiao, "Oriented Response Networks," IEEE CVPR, 2017. [pdf]-[source code]-[bibtex]

Object Detection (older)

[63] S. Gao, Q. Ye,  K. Arjan, L. Liu, X. Ji, A Graphical Social Topology Model for RGB-D Multi-Person Tracking,  IEEE Trans. Circuits Syst. Video Technol. (T-CSVT) 10.1109/TCSVT.2021.3049397, 2020. [pdf]

[64] Y. Cai, W. Wang, Y. Chen, Q. Ye, "IOS-Net: An Inside-to-outside Supervision Network for Scale Robust Text Detection in the wild,"  Pattern Recognition, 2020 [pdf].

[65]  F.  Liang, L. Duan, W. Ma, Y. Qiao, J. Miao, Q. Ye, Context-aware Network for RGB-D Salient Object Detection,  Pattern Recognition, 2020( (To Appear).

[66] F. Liang, L. Duan, W. Ma, Y. Qiao, Z. Cai, J. Miao, Q. Ye, "CoCNN: RGB-D Deep Fusion for Stereoscopic Salient Object Detection," Patter Recognition. 104: 107329 (2020). [pdf].

[67] X. Yu, Y. Gong, N. Jiang, Q. Ye, Z. Han,"Scale-match for Tiny Person Detection,"  WACV, 2020 [pdf].

[68] T. Zhang, Z. Han, H. Xu, B. Zhang, Q. Ye, "CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection,"  IEEE Trans. Intell. Transp. Syst. (T-ITS), 2019 [pdf].

[69] C. Li, B. Zhang, Q. Ye,  "Deep Manifold Structure Transfer for Action Recognition," IEEE Trans. Image Process. (TIP) 28(9): 4646-4658 (2019). [pdf]

[70] X. Liu, C. Li, H. Wang, X. Zhen, B. Zhang, Q. Ye, "Starts Better and Ends Better: A Target Adaptive Image Signature Tracker,"  WACV, 2019.

[71Q. Ye, T. Zhang  "Progressive Latent Model for Self-learning Scene-specific Pedestrian Detectors,"  IEEE Trans. Intell. Transp. Syst. (T-ITS), 10.1109/TITS.2019.2911315, 2020.[pdf].

[72] Z. Han, P. Wang, Q. Ye, "Adaptive Discriminative Deep Correlation Filter for Visual Object Tracking," IEEE Trans. Circuits Syst. Video Technol. (T-CSVT) 30(1): 155-166 (2020). [pdf]

[73] P. Wei, F. Qin, F. Wan, Y. Zhu, J. Jiao and Q. Ye, "Correlated Topic Vector for Scene Classification", IEEE Trans Image Process. (TIP), 26(7):3221-3234 (2017). [pdf]-[bibtex]

[74] S. Gao, Q. Ye, J. Xing, A. kuijper, Z. Han, J. Jiao, X. Ji, "Beyond Group: Multiple Person Tracking via Minimal Topology-Energy-Variation," IEEE Trans. Image Process. (TIP), 26(12):5575-5589 (2017)[pdf]-[bibtex]

[75] B. Zhang, Z. Li, X. Cao, Q. Ye, C. Chen, L. Shen, A. Perina, and R. Ji,"Output Constraint Transfer for Kernelized Correlation Filter in Tracking," IEEE Trans. Systems, Man, and Cybernetics, 47(4):693-703 (2017).  [pdf]-[bibtex]

[76Q. Ye, D. S. Doermann, "Text Detection and Recognition in Imagery: A Survey,"  IEEE Trans. Pattern Anal. Mach. Intell. (PAMI), 37(3):1480-1500 (2015). [pdf]-[bibtex]

[77] S. Gao, Z. Han, C. Li, Q. Ye, J. Jiao, "Real-time Multi-pedestrian Tracking in Traffic Scenes via an RGB-D based Layered Graph Model,"  IEEE Trans. Intell. Transp. Syst. (T-ITS), 16(5): 2814-2825 (2015). [pdf]-[bibtex]

[78] L. Zhang, Q. Ye, W. Yang, J. Jiao, "Weld Line Detection and Tracking via Spatial-Temporal Cascaded Hidden Markov Models and Cross Structured Light," IEEE Trans. Instru. and Measure. (TIM), 6(4):742-752 (2014). [pdf]-[bibtex]

[79Q. Ye, Z. Han, J. Jiao, J. Liu, "Human Detection in Images via Piecewise Linear Support Vector Machines," IEEE TransImage Process. (TIP), 22(2):778-789 (2013). [pdf]- [source code]-[bibtex

[80Q. Ye, J. Liang, J. Jiao, "Pedestrian Detection in Video Images via Error Correcting Output Code Classification of Manifold Subclasses," IEEE Trans. Intell. Transp. Syst. (T-ITS), 13(1): 193-202 (2012). [pdf]-[bibtex]

[81] R. Xu, J. Jiao, B. Zhang, Q. Ye, "Pedestrian Detection in Images via Cascaded L1-norm Minimization Learning Method," Pattern Recognition, 45(7):2573-2583 (2012). [pdf]-[bibtex]

[82] Z. Han, J. Jiao, Q. Ye, J. Liu, "Visual Object Tracking Via Sample-Based Adaptive Sparse Representation, " Pattern Recognition, 44(9): 2170-2183 (2011). [pdf]-[bibtex]

[83叶齐祥,焦建彬,蒋树强,基于多尺度方向特征的快速鲁棒人体检测算法,软件学报2011,22(12):3004-3014.  [pdf]

[84] R. Xu, B. Zhang, Q. Ye, J. Jiao, "Cascaded L1-norm Minimization Learning (CLML) Classifier for Human Detection," IEEE CVPR, 2010. [pdf]-[bibtex].

[85] J. Jiao, Q. Ye, Q. Huang, "A Configurable Method for Multi-style License Plate Recognition," Pattern Recognition,  32(3):358--369, 2009. [pdf]-[bibtex]

[86Q.  Ye, Q. Huang, W. Gao, S. Jiang, "Exciting event detection in broadcast soccer video with mid-level description and incremental learning," ACM Multimedia pp.455-458, 2005. [pdf]

[87] Q. Ye, Q. Huang, W. Gao, D. Zhao, "Fast and robust text detection in images and video frames," Image Vis. Comput. (IVC) 23(6): 565-576 (2005). [pdf]


[89] Q. Ye, W. Gao, W. Zeng, "Color image segmentation using density-based clustering," IEEE ICASSP (3) 2003: 345-348. [pdf]


Machine Learning from 2014-2020 Slides
Reinforecment Learning: from AlhpaGo to AlphaZero 2018 Spring, 2019 Spring slides