[Book1-1]
Essentials of Pattern Recognition: An Accessible Approach [Textbook homepage]
Jianxin Wu
Cambridge University Press, Dec. 2020, ISBN 9781108483469 (hardback), 9781108650212 (online)
[Book1-2]
模式识别 [教材主页]
吴建鑫 著 （罗建豪、张皓 译； 吴建鑫 审校）
机械工业出版社, 2020年1月, ISBN 978-7-111-64389-0
(这是 Book1-1 的中文版)
[B3]
结构化剪枝综述
[PDF]
吴建鑫, 王环宇, 张永顺
In 张敏灵，胡清华，李宇峰 eds. 机器学习及其应用(2021), 清华大学出版社, 2021.
[B2]
Face Detection
[Chapter page in SpringerLink]
Stan Z. Li and Jianxin Wu
Chapter 11, in S. Z. Li and A. K. Jain eds. Handbook of Face Recognition (2nd edition), Springer, 2011, pages 277-303.
[B1]
Object Detection
Chapter page in SpringerLink]
Jianxin Wu and James M. Rehg
s
Chapter 8, in C. Zhang and Y. Ma eds. Ensemble Machine Learning: Methods and Applications, Springer, 2012, pages 225-250.
[J.57]
DTL: Parameter- and Memory-Efficient Disentangled Vision Learning [pdf][Appendix]
Minghao Fu, Ke Zhu, Zonghao Ding, Jianxin Wu
IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(2), 2026: 1736-1749
[J.56]
Coarse Is Better? A New Pipeline Towards Self-Supervised Learning with Uncurated Images [pdf]
Ke Zhu, Yin-Yin He, Jianxin Wu
Pattern Recognition, Vol. 161, Article 111324, 2025.
[J.55]
Reviving Undersampling for Long-tailed Learning [pdf][Code]
Hao Yu, Yingxiao Du, Jianxin Wu
Pattern Recognition, Vol. 161, Article 111200, 2025.
[J.54]
Practical Network Acceleration with Tiny Sets: Hypothesis, Theory, and Algorithm [pdf]
Guo-Hua Wang, Jianxin Wu
IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 2024: 9272-9285.
[J.53]
Tobias: A Random CNN Sees Objects [pdf][Code]
Yun-Hao Cao, Jianxin Wu
IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(2), 2024: 1290-1304.
[J.52]
Salvage of Supervision in Weakly Supervised Object Detection and Segmentation [Paper PDF][Appendix][Code]
Lin Sui, Chen-Lin Zhang, Jianxin Wu
IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8), 2023: 10394-10408.
[J.51]
Random Subspace Sampling for Classification with Missing Data [pdf]
Yun-Hao Cao, Jianxin Wu
Journal of Computer Science and Technology, 39(2), 2024: 472-486.
[J.50]
Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection [pdf]
Chen-Lin Zhang, Yin Li, Jianxin Wu
Pattern Recognition, Vol. 137, Article 109279, 2023.
[J.49]
A Unified Pruning Framework for Vision Transformers [pdf][appendix]
Hao Yu, Jianxin Wu
SCIENCE CHINA Information Sciences, 66(7), Article 179101, 2023.
[J.48]
Versatile, Full-spectrum, and Swift Network Sampling for Model Generation [pdf]
Huanyu Wang, Yongshun Zhang, Jianxin Wu
Pattern Recognition, Vol. 129, Article 108729, 2022.
Please note that the formal PDF in the journal has an error: the typesetter changed our article such that the second last paragraph above section 4.4 contains errors. The draft PDF here is correct.
[J.47]
Fine-Grained Image Analysis with Deep Learning: A Survey [pdf]
Xiu-Shen Wei, Yi-Zhe Song, Oisin Mac Aodha, Jianxin Wu, Yuxin Peng, Jinhui Tang, Jian Yang, Serge Belongie
IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12), 2022: 8927-8948.
[J.46]
Distilling Knowledge by Mimicking Features [pdf]
Guo-Hua Wang, Yifan Ge, Jianxin Wu
IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11), 2022: 8183-8195.
[J.45]
Neural Random Subspace [pdf]
Yun-Hao Cao, Jianxin Wu, Hanchen Wang, Joan Lasenby
Pattern Recognition, Vol. 112, Article 107801, 2021.
[J.44]
Simultaneous 3D Hand Detection and Pose Estimation using Single Depth Images
Yu Zhang, Siya Ma, Jianxin Wu, Xin Geng
Pattern Recognition Letters, Vol. 140, 2020: 43-48.
[J.43]
ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification [pdf]
Fu Xiong, Yang Xiao, Zhiguo Cao, Yancheng Wang, Joey Tianyi Zhou, Jianxin Wu
IEEE Transactions on Cybernetics, 52(3), 2022: 1736-1749.
[J.42]
AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference [pdf]
Jian-Hao Luo, Jianxin Wu
Pattern Recognition, Vol. 107, Article 107461, 2020.
[J.41]
Multi-Instance Learning with Emerging Novel Class [pdf]
Xiu-Shen Wei, Han-Jia Ye, Jianxin Wu, Chunhua Shen, Zhi-Hua Zhou
IEEE Transactions on Knowledge and Data Engineering, 33(5), 2021: 2109-2120.
[J.40]
Piecewise Classifier Mappings: Learning Fine-grained Learners for Novel Categories with Few Examples [pdf]
Xiu-Shen Wei, Peng Wang, Lingqiao Liu, Chunhua Shen, Jianxin Wu
IEEE Transactions on Image Processing, 28(12), 2019: 6116-6125.
[J.39]
Improving CNN Linear Layers with Power Mean Non-Linearity [pdf]
Chen-Lin Zhang, Jianxin Wu
Pattern Recognition, 89, 12-21, 2019.
Please note that the formal PDF in the journal has an error: rates in the last two rows in Table 4 need to be switched: ResNet-50 mAP should be 76.60%, while ResNet-50 w/ pm-o should be 77.60%. The draft PDF here is correct.
[J.38]
Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transformation [pdf][project page]
Xiu-Shen Wei, Chen-Lin Zhang, Jianxin Wu, Chunhua Shen, Zhi-Hua Zhou
Pattern Recognition, 88, 113-126, 2019.
[J.37]
ThiNet: Pruning CNN Filters for a Thinner Net [pdf]
Jian-Hao Luo, Hao Zhang, Hong-Yu Zhou, Chen-Wei Xie, Jianxin Wu, Weiyao Lin
IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(10), 2019: 2525-2538.
[J.36]
CodeAttention: Translating Source Code to Comments by Exploiting the Code Constructs [pdf]
Wenhao Zheng, Hong-Yu Zhou, Ming Li, Jianxin Wu
Frontiers of Computer Science, 13(3), 2019: 565-578.
[J.35]
资源受限的深度学习：挑战与实践(in Chinese) [Download PDF from publisher's page]
Jianxin Wu, Bin-Bin Gao, Xiu-Shen Wei, Jian-Hao Luo
中国科学: 信息科学(SCIENTIA SINICA Informationis), 48(5), 2018: 501-510.
[J.34]
Deep Bimodal Regression of Apparent Personality Traits from Short Video Sequences [pdf] [Project page with links to code]
Xiu-Shen Wei, Chen-Lin Zhang, Hao Zhang, Jianxin Wu
IEEE Transactions on Affective Computing, 9(3), 2018: 303-315.
[J.33]
Mask-CNN: Localizing parts and selecting descriptors for fine-grained bird species categorization [pdf]
Xiu-Shen Wei, Chen-Wei Xie, Jianxin Wu, and Chunhua Shen
Pattern Recognition, 76, 2018: 704-714.
[J32]
Deep Label Distribution Learning with Label Ambiguity [pdf] [project page]
Bin-Bin Gao, Chao Xing, Chen-Wei Xie, Jianxin Wu, and Xin Geng
IEEE Transactions on Image Processing, 26(6), 2017: 2825-2838.
[J31]
Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval [pdf] [project page]
Xiu-Shen Wei, Jian-Hao Luo, Jianxin Wu, and Zhi-Hua Zhou
IEEE Transactions on Image Processing, 26(6), 2017: 2868-2881.
[J30]
Learning Correspondence Structures for Person Re-identification [pdf]
Weiyao Lin, Yang Shen, Junchi Yan, Mingliang Xu, Jianxin Wu, Jingdong Wang, and Ke Lu
IEEE Transactions on Image Processing, 26(5), 2017: 2438-2453.
[J29]
Structured Learning of Binary Codes with Column Generation for Optimizing Ranking Measures [SpringerLink page]
Guosheng Lin, Fayao Liu, Chunhua Shen, Jianxin Wu, Heng Tao Shen
International Journal of Computer Vision, 123(2), 2017: 287-308.
[J28]
A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories [pdf]
Weiyao Lin, Yang Zhou, Hongteng Xu, Junchi Yan, Mingliang Xu, Jianxin Wu, and Zicheng Liu
IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(8), 2017: pp. 1489-1503.
[J27]
Action Recognition in Still Images with Minimum Annotation Efforts [pdf]
Yu Zhang, Li Cheng, Jianxin Wu, Jianfei Cai, Minh N. Do, Jiangbo Lu
IEEE Transactions on Image Processing, 25(11), 2016: pp. 5479-5490.
[J26]
Image Categorization with Resource Constraints: Introduction, Challenges and Advances [pdf]
Jian-Hao Luo, Wang Zhou, Jianxin Wu
Frontiers of Computer Science, 11(1), 2017: pp. 13-26.
[J25]
Minimal Gated Unit for Recurrent Neural Networks [pdf]
Guo-Bing Zhou, Jianxin Wu, Chen-Lin Zhang, Zhi-Hua Zhou
International Journal of Automation and Computing, 13(3), 2016: pp. 226-234.
[J24]
Compact Representation of High-Dimensional Feature Vectors for Large-Scale Image Recognition and Retrieval [pdf]
Yu Zhang, Jianxin Wu, Jianfei Cai
IEEE Transactions on Image Processing, 25(5), 2016: pp. 2407-2419.
[J23]
A Diffusion and Clustering-based Approach for Finding Coherent Motions and Understanding Crowd Scenes [pdf]
Weiyao Lin, Yang Mi, Weiyue Wang, Jianxin Wu, Jingdong Wang, Tao Mei
IEEE Transactions on Image Processing, 25(4), 2016: pp. 1674-1687.
[J22]
Weakly Supervised Fine-Grained Categorization with Part-Based Image Representation [pdf]
Yu Zhang, Xiu-Shen Wei, Jianxin Wu, Jianfei Cai, Jiangbo Lu, Viet-Anh Nguyen, Minh N. Do
IEEE Transactions on Image Processing, 25(4), 2016: pp. 1713-1725.
[J21]
Scalable Algorithms for Multi-Instance Learning [pdf] [project page]
Xiu-Shen Wei, Jianxin Wu, Zhi-Hua Zhou
IEEE Transactions on Neural Networks and Learning Systems, 28(4), 2017: pp. 975-987.
[J20]
Good Practices for Learning to Recognize Actions using FV and VLAD [pdf]
Jianxin Wu, Yu Zhang, Weiyao Lin
IEEE Transactions on Cybernetics, 46(12), 2016: pp. 2978-2990.
[J19]
Linear Regression Based Efficient SVM Learning for Large Scale Classification [pdf]
Jianxin Wu, Hao Yang
IEEE Transactions on Neural Networks and Learning Systems, 26(10), 2015: pp. 2357-2369.
[J18]
Automatic Face Naming by Learning Discriminative Affinity Matrices from Weakly Labeled Images [pdf]
Shijie Xiao, Dong Xu, Jianxin Wu
IEEE Transactions on Neural Networks and Learning Systems, 26(10), 2015: 2440-2452.
[J17]
Flexible Image Similarity Computation Using Hyper-Spatial Matching [pdf]
Yu Zhang, Jianxin Wu, Jianfei Cai, Weiyao Lin
IEEE Transactions on Image Processing, 23(9), 2014: pp. 4112-4125.
[J16]
GROPING: Geomagnetism and cROwdsensing Powered Indoor NaviGation [pdf]
Chi Zhang, Kalyan P. Subbu, Jun Luo, Jianxin Wu
IEEE Transactions on Mobile Computing, 14(2), 2015: pp. 387-400.
[J15]
Facial expression cloning with elastic and muscle models [pdf]
Yihao Zhang, Weiyao Lin, Bing Zhou, Zhenzhong Chen, Bin Sheng, Jianxin Wu
Journal of Visual Communication and Image Representation, 25(5), 2014: pp. 916-927.
[J14]
mCENTRIST: A Multi-channel Feature Generation Mechanism for Scene Categorization [pdf][Code]
Yang Xiao, Jianxin Wu and Junsong Yuan
IEEE Transactions on Image Processing, 23(2), 2014: pp. 823-836.
[J13]
A New Network-based Algorithm for Human Activity Recognition in Videos [pdf]
Weiyao Lin, Yuanzhe Chen, Jianxin Wu, Hanli Wang, Bin Sheng, Hongxiang Li
IEEE Transactions on Circuits and Systems for Video Technology, 24(5), 2014: pp. 826-841.
[J12]
C4: A Real-time Object Detection Framework [pdf][project page with source code][C4 mirror page]
Jianxin Wu, Nini Liu, Christopher Geyer and James M. Rehg
IEEE Transactions on Image Processing, 22(10), 2013: pp. 4096-4107.
[J11]
A Heat-Map-based Algorithm for Recognizing Group Activities in Videos
Weiyao Lin, Hang Chu, Jianxin Wu, Bin Sheng, and Zhenzhong Chen
IEEE Transactions on Circuits and Systems for Video Technology, 23(11), 2013: pp. 1980-1992.
[J10]
Efficient HIK SVM Learning for Image Classification [pdf][project page with source code: libHIK][libHIK mirror page]
Jianxin Wu
IEEE Transactions on Image Processing, 21(10), 2012: pp. 4442-4453.
[J9]
Probabilistic Classifiers with a Generalized Gaussian Scale Mixture Prior [pdf]
Guoqing Liu, Jianxin Wu, and Suiping Zhou
Pattern Recognition, 46(1), 2013: pp. 332-345.
[J8]
Efficient and Effective Visual Codebook Generation Using Additive Kernels [pdf][project page with source code: libHIK][libHIK mirror page]
Jianxin Wu, Wei-Chian Tan, and James M. Rehg
Journal of Machine Learning Research, 12(Nov), 2011: pp. 3097-3118.
[J7]
CENTRIST: A Visual Descriptor for Scene Categorization [pdf][project page with source code: libHIK for CENTRIST, and PACT][libHIK mirror page]
Jianxin Wu and James M. Rehg
IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(8), 2011: pp. 1489-1501.
[J6]
Exploratory Under-Sampling for Class-Imbalance Learning [pdf][project page with source code]
Xu-Ying Liu, Jianxin Wu, and Zhi-Hua Zhou
IEEE Transactions on Systems, Man, and Cybernetics -- Part B: Cybernetics, 39(2), 2009: pp. 539-550.
[J5]
Fast Asymmetric Learning for Cascade Face Detection [pdf][project page with source code]
Jianxin Wu, S. Charles Brubaker, Matthew D. Mullin, and James M. Rehg
IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(3), 2008: pp. 369-382.
[J4]
On the Design of Cascades of Boosted Ensembles for Face Detection [SpringerLink page]
S. Charles Brubaker, Jianxin Wu, Jie Sun, Matthew D. Mullin, and James M. Rehg
International Journal of Computer Vision, 77(1-3), 2008, pp.65-86.
[J3]
Efficient Face Candidates Selector for Face Detection [pdf][project page with demo]
Jianxin Wu and Zhi-Hua Zhou
Pattern Recognition, 36(5), 2003: 1175-1186.
[J2]
Ensembling Neural Networks: Many Could Be Better Than All [pdf][project page with source code]
Zhi-Hua Zhou, Jianxin Wu, and Wei Tang
Artificial Intelligence, 137(1-2), 2002: 239-263.
[J1]
Face Recognition with One Training Image per Person [pdf][project page with data information]
Jianxin Wu and Zhi-Hua Zhou
Pattern Recognition Letters, 23(14), 2002: 1711-1719.
[C.84]
TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies [pdf][Appendix]
Guang Liang, Jie Shao, Ningyuan Tang, Xinyao Liu, Jianxin Wu
Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026), Denver, Colorado, USA, Jun. 2026, pp xx-xx.
[C.83]
Who Reasons in the Large Language Models? [pdf]
Jie Shao, Jianxin Wu
In: Proc. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), San Diego, CA, USA, Dec. 2025, pp. 113087-113108.
[C.82]
GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers [pdf][Code]
Guang Liang, Xinyao Liu, Jianxin Wu
In: Proc. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), San Diego, CA, USA, Dec. 2025, pp. 7033-7057.
[C.81]
Dual DTL: Double-Side Compact Transfer Networks for Efficient ViT Adaptation [pdf]
Zonghao Ding, Minghao Fu, Jianxin Wu
In: Proc. 8th Chinese Conference on Pattern Recognition and Computer Vision (PRCV 2025), Shanghai, China, October 2025, LNCS vol. 16273, pp. 375-387.
[C.80]
Memory-Efficient Generative Models via Product Quantization [pdf][appendix]
Jie Shao, Hanxiao Zhang, Hao Yu, Jianxin Wu
In: Proc. International Conference on Computer Vision (ICCV 2025), Honolulu, Hawaii, USA, October 2025, pp. xx-xx.
[C.79]
Minimal Interaction Separated Tuning: A New Paradigm for Visual Adaptation [pdf]
Ningyuan Tang, Minghao Fu, Jianxin Wu
In: Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), Nashville, TN, Jun. 2025, pp. 25208-25217.
[C.78]
Quantization without Tears [pdf][Code] An error corrected in this version on July 2025. Please refer to the "Correction Note" Section for details
Minghao Fu, Hao Yu, Jie Shao, Junjie Zhou, Ke Zhu, Jianxin Wu
In: Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), Nashville, TN, Jun. 2025, pp. 4462-4472.
[C.77]
Treasures in Discarded Weights for LLM Quantization [pdf]
Hao Yu, Yang Zhou, Bohua Chen, Zelan Yang, Shen Li, Yong Li, Jianxin Wu
In: Proc. the 39th AAAI Conference on Artificial Intelligence (AAAI 2025), Philadelphia, PA, USA, Feb.-Mar. 2025, pp. 22218-22226.
[C.76]
All You Need in Knowledge Distillation Is a Tailored Coordinate System [pdf]
Junjie Zhou, Ke Zhu, Jianxin Wu
In: Proc. the 39th AAAI Conference on Artificial Intelligence (AAAI 2025), Philadelphia, PA, USA, Feb.-Mar. 2025, pp. 22946-22954.
[C.75]
DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge [pdf]
Jie Shao, Ke Zhu, Hanxiao Zhang, Jianxin Wu
In: Proc. Advances in Neural Information Processing Systems 38 (NeurIPS 2024), Vancouver, Canada, Dec. 2024, pp. 123007-123031.
[C.74]
Rectify the Regression Bias in Long-Tailed Object Detection [pdf]
Ke Zhu, Minghao Fu, Jie Shao, Tianyu Liu, Jianxin Wu
In: Proc. 18th European Conference on Computer Vision (ECCV 2024), Milan, Italy, Sep.-Oct. 2024, LNCS vol. 15086, pp. 198-214.
[C.73]
Unified Low-rank Compression Framework for Click-through Rate Prediction [pdf]
Hao Yu, Minghao Fu, Jiandong Ding, Yusheng Zhou, Jianxin Wu
In: Proc. 30th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2024, Applied Data Science track), Barcelona, Spain, Aug. 2024, pp. 6169-6180.
[C.72]
Instance-based Max-margin for Practical Few-shot Recognition [pdf]
Minghao Fu, Ke Zhu, Guo-Hua Wang
In: Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, Jun. 2024, pp. 28674-28683.
I am very heavily involved in this IbM2 work (wrote IbM2's first version of code), but my name cannot appear---CVPR PCs not allowed to submit papers.
[C.71]
Dense Vision Transformer Compression with Few Samples [pdf][Code]
Hanxiao Zhang, Yifan Zhou, Guo-Hua Wang
In: Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, Jun. 2024, pp. 15825-15834.
I am heavily involved in this DCViT work, but my name cannot appear---CVPR PCs not allowed to submit papers.
[C.70]
DTL: Disentangled Transfer Learning for Visual Recognition [pdf] [Appendix]
Minghao Fu, Ke Zhu, Jianxin Wu
In: Proc. the 38th AAAI Conference on Artificial Intelligence (AAAI 2024), Vancouver, Canada, Feb. 2024, pp. 12082-12090.
[C.69]
Multi-Label Self-Supervised Learning with Scene Images [pdf] [Appendix]
Ke Zhu, Minghao Fu, Jianxin Wu
In: Proc. International Conference on Computer Vision (ICCV 2023), Paris, France, October 2023, pp. 6694-6703.
[C.68]
No One Left Behind: Improving the Worst Categories in Long-Tailed Learning [pdf] [Appendix]
Yingxiao Du, Jianxin Wu
In: Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, June 2023, pp. 15804-15813.
[C.67]
Practical Network Acceleration with Tiny Sets [pdf] [Code]
Guo-Hua Wang, Jianxin Wu
In: Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, June 2023, pp. 20331-20340.
[C.66]
Compressing Transformers: Features Are Low-Rank, but Weights Are Not! [pdf]
Hao Yu, Jianxin Wu
In: Proc. the 37th AAAI Conference on Artificial Intelligence (AAAI 2023), Washington DC, USA, Feb. 2023, pp. 11007-11015.
[C.65]
Quantized Feature Distillation for Network Quantization [pdf]
Ke Zhu, Yin-Yin He, Jianxin Wu
In: Proc. the 37th AAAI Conference on Artificial Intelligence (AAAI 2023), Washington DC, USA, Feb. 2023, pp. 11452-11460.
[C.64]
ActionFormer: Localizing Moments of Actions with Transformers [pdf] [appendix]
Chen-Lin Zhang, Jianxin Wu, Yin Li
In: Proc. The 17th European Conference on Computer Vision (ECCV 2022), Tel Aviv, Israel, Oct. 2022, LNCS vol. 13664, pp. 492-510.
[C.63]
Worst Case Matters for Few-Shot Recognition [pdf]
Minghao Fu, Yun-Hao Cao, Jianxin Wu
In: Proc. The 17th European Conference on Computer Vision (ECCV 2022), Tel Aviv, Israel, Oct. 2022, LNCS vol. 13680, pp. 99-115.
[C.62]
Synergistic Self-supervised and Quantization Learning [pdf][code]
Yun-Hao Cao, Peiqin Sun, Yechang Huang, Jianxin Wu, Shuchang Zhou
In: Proc. The 17th European Conference on Computer Vision (ECCV 2022), Tel Aviv, Israel, Oct. 2022, LNCS vol. 13690, pp. 587-604.
[C.61]
Training Vision Transformers with Only 2040 Images [pdf][code]
Yun-Hao Cao, Hao Yu, Jianxin Wu
In: Proc. The 17th European Conference on Computer Vision (ECCV 2022), Tel Aviv, Israel, Oct. 2022, LNCS vol. 13685, pp. 220-237.
[C.60]
Compressing Models with Few Samples: Mimicking then Replacing [pdf]
Huanyu Wang, Junjie Liu, Xin Ma, Yang Yong, Zhenhua Chai, Jianxin Wu
In: Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, USA, June 2022, pp. 701-710.
[C.59]
Salvage of Supervision in Weakly Supervised Object Detection [pdf][appendix][code]
Lin Sui, Chen-Lin Zhang, Jianxin Wu
In: Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, USA, June 2022, pp. 14227-14236.
[C.58]
A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications [pdf]
Yun-Hao Cao, Jianxin Wu
In: Proc. the 36th AAAI Conference on Artificial Intelligence (AAAI 2022), Virtual, Feb. 2022, pp. 194-202.
[C.57]
Residual Attention: A Simple but Effective Method for Multi-Label Recognition [pdf]
Ke Zhu, Jianxin Wu
In: Proc. International Conference on Computer Vision (ICCV 2021), Virtual, October 2021, pp. 184-193.
[C.56]
Distilling Virtual Examples for Long-tailed Recognition [pdf]
Yin-Yin He, Jianxin Wu, Xiu-Shen Wei
In: Proc. International Conference on Computer Vision (ICCV 2021), Virtual, October 2021, pp. 235-244.
[C.55]
Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach [pdf]
Zeren Sun, Yazhou Yao, Xiu-Shen Wei, Yongshun Zhang, Fumin Shen, Jianxin Wu, Jian Zhang, Heng Tao Shen
In: Proc. International Conference on Computer Vision (ICCV 2021), Virtual, October 2021, pp. 10602-10611.
[C.54]
Mixup without Hesitation [pdf]
Hao Yu, Huanyu Wang, and Jianxin Wu
In: Proc. the 11th International Conference on Image and Graphics (ICIG 2021), Haikou, China, November 2021, pp. LNCS 12889, pp. 143-154.
[C.53]
Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural Networks [pdf]
Yongshun Zhang, Xiu-Shen Wei, Boyan Zhou, Jianxin Wu
In: Proc. the 35th AAAI Conference on Artificial Intelligence (AAAI 2021), Virtual Conference, Feb. 2021, pp. 3447-3455.
[C.52]
Rethinking the Route Towards Weakly Supervised Object Localization [pdf]
Chen-Lin Zhang, Yun-Hao Cao, Jianxin Wu
In: Proc. The IEEE Int'l Conference on Computer Vision and Pattern Recognition (CVPR 2020), Virtual Conference, Jun. 2020, pp. 13460-13469.
[C.51]
Neural Network Pruning with Residual-Connections and Limited-Data [pdf]
Jian-Hao Luo, Jianxin Wu
In: Proc. The IEEE Int'l Conference on Computer Vision and Pattern Recognition (CVPR 2020), Virtual Conference, Jun. 2020, pp. 1458-1467.
[C.50]
Repetitive Reprediction Deep Decipher for Semi-Supervised Learning [pdf]
Guo-Hua Wang, Jianxin Wu
In: Proc. the 34th AAAI Conference on Artificial Intelligence (AAAI 2020), New York, NY, USA, Feb. 2020, pp. 6170-6177.
[C.49]
Deep Discriminative CNN with Temporal Ensembling for Ambiguously-Labeled Image Classification [pdf]
Yao Yao, Jiehui Deng, Xiuhua Chen, Chen Gong, Jianxin Wu, Jian Yang
In: Proc. the 34th AAAI Conference on Artificial Intelligence (AAAI 2020), New York, NY, USA, Feb. 2020, pp. 12669-12676.
[C.48]
Probabilistic End-to-end Noise Correction for Learning with Noisy Labels [pdf] [ Code]
Kun Yi, Jianxin Wu
In: Proc. The IEEE Int'l Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, USA, Jun. 2019, pp. 7017-7025.
[C.47]
Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification [pdf]
Xiu-Shen Wei, Chen-Lin Zhang, Lingqiao Liu, Chunhua Shen, Jianxin Wu
In: Proc. 14th Asian Conference on Computer Vision (ACCV 2018), Perth, Australia, December 2018, LNCS 11362, pp. 575-591.
[C.46]
Age Estimation Using Expectation of Label Distribution Learning [pdf] [project page]
Bin-Bin Gao, Hong-Yu Zhou, Jianxin Wu, Xin Geng
In: Proc. the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), Stockholm, Sweden, July 2018, pp. 712--718.
[C.45]
Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion [pdf]
Weiyao Lin, Yang Mi, Jianxin Wu, Ke Lu, Hongkai Xiong
In: Proc. the 32th AAAI Conference on Artificial Intelligence (AAAI 2018), New Orleans, Louisiana, USA, Feb 2018, pp. 7130-7137.
[C.44]
Content-Based Image Recovery [pdf]
Hong-Yu Zhou, Jianxin Wu
In: Proc. Pacific-Rim Conference on Multimedia (PCM 2017), Harbin, China, October 2017, LNCS vol. 10736, pp. 606-615.
[C.43]
In Defense of Fully Connected Layers in Visual Representation Transfer [pdf]
Chen-Lin Zhang, Jian-Hao Luo, Xiu-Shen Wei, Jianxin Wu
In: Proc. Pacific-Rim Conference on Multimedia (PCM 2017), Harbin, China, October 2017, LNCS vol. 10736, pp. 807-817.
[C.42]
Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors [pdf] [project page]
Hong-Yu Zhou, Bin-Bin Gao, Jianxin Wu
In: Proc. International Conference on Computer Vision (ICCV 2017), Venice, Italy, October 2017, pp. 3505-3513.
[C.41]
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression [pdf] [project page]
Jian-Hao Luo, Jianxin Wu, Weiyao Lin
In: Proc. International Conference on Computer Vision (ICCV 2017), Venice, Italy, October 2017, pp. 5058-5066.
[C.40]
Sunrise or Sunset: Selective Comparison Learning for Subtle Attribute Recognition [pdf] [project page]
Hong-Yu Zhou, Bin-Bin Gao, Jianxin Wu
In: Proc. The 28th British Machine Vision Conference (BMVC 2017), London, UK, September 2017.
[C.39]
Deep Descriptor Transforming for Image Co-Localization [pdf] [code]
Xiu-Shen Wei, Chen-Lin Zhang, Yao Li, Chen-Wei Xie, Jianxin Wu, Chunhua Shen, Zhi-Hua Zhou
In: Proc. The 26th International Joint Conference on Artificial Intelligence (IJCAI 2017), Melbourne, Australia, August 2017, pp. 3048-3054.
[C38]
Exploit Bounding Box Annotations for Multi-label Object Recognition [pdf]
Hao Yang, Joey Tianyi Zhou, Yu Zhang, Bin-Bin Gao, Jianxin Wu, Jianfei Cai
In: Proc. The IEEE Int'l Conference on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, USA, Jun. 2017, pp. 280-288.
[C37]
Learning Compact Binary Codes from Higher-Order Tensors via Free-Form Reshaping and Binarized Multilinear PCA
[pdf]
Haiping Lu, Jianxin Wu, and Yu Zhang
In: Proc. the Annual International Joint Conference on Neural Networks (IJCNN2016), Vancouver, Canada, July 2016, pp. 3008-3015.
[C.36]
Representing Sets of Instances for Visual Recognition [pdf]
Jianxin Wu, Bin-Bin Gao, Guoqing Liu
In: Proc. the 30th AAAI Conference on Artificial Intelligence (AAAI 2016), Phoenix, Arizona, USA, Feb 2016, pp. 2237-2243.
[C35]
Person Re-identification with Correspondence Structure Learning [pdf]
Yang Shen, Weiyao Lin, Junchi Yan, Mingliang Xu, Jianxin Wu, Jingdong Wang
In: Proc. International Conference on Computer Vision (ICCV 2015), Santigao, Chile, Dec 2015, pp. 3200-3208.
[C.34]
Learning with Augmented Multi-Instance View [pdf]
Yue Zhu, Jianxin Wu, Yuan Jiang and Zhi-Hua Zhou
In: Proc. 6th Asian Conference on Machine Learning (ACML 2014), Nha Trang, Vietnam, Nov 2014, JMLR W&CP 39:234-249, 2014.
[C33]
Scalable Multi-Instance Learning [pdf][code]
Xiu-Shen Wei, Jianxin Wu and Zhi-Hua Zhou
In: Proc. IEEE International Conference on Data Mining (ICDM 2014), Shenzhen, China, Dec 2014, pp. 1037-1042. (short paper)
[C.32]
Representing and Recognizing Motion Trajectories: A Tube and Droplet Approach [pdf]
Yang Zhou, Weiyao Lin, Hang Su, Jianxin Wu, Jinjun Wang, Yu Zhou
In: Proc. 22nd ACM International Conference on Multimedia (MM 2014), Orlando, FL, USA, Nov 2014, pp. 1077-1080. (short paper)
[C31]
Optimizing Ranking Measures for Compact Binary Code Learning [pdf]
Guosheng Lin, Chunhua Shen, Jianxin Wu
In: Proc. The 13th European Conference on Computer Vision (ECCV 2014), Zürich, Switzerland, Sep. 2014, LNCS vol. 8691, pp. 613-627.
[C30]
Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach [pdf]
Weiyue Wang, Weiyao Lin, Yuanzhe Chen, Jianxin Wu, Jingdong Wang, and Bin Sheng
In: Proc. The 13th European Conference on Computer Vision (ECCV 2014), Zürich, Switzerland, Sep. 2014, LNCS vol. 8689, pp. 756-771.
[C29]
A Dual-Sensor Enabled Indoor Localization System with Crowdsensing Spot Survey [pdf]
Chi Zhang, Jun Luo, Jianxin Wu
In: Proc. The 10th IEEE/ACM International Conference on Distributed Computing in Sensor Systems (DCOSS 2014), Marina Del Rey, CA, USA, May 2014, pp. 75-82.
[C28]
Compact Representation for Image Classification: To Choose or to Compress? [pdf][MI-based Feature Selection Matlab Code]
Yu Zhang, Jianxin Wu, Jianfei Cai
In: Proc. The IEEE Int'l Conference on Computer Vision and Pattern Recognition (CVPR 2014), Columbus, OH, USA, Jun. 2014, pp. 907-914.
[C27]
Towards Good Practices for Action Video Encoding [pdf]
Jianxin Wu, Yu Zhang, Weiyao Lin
In: Proc. The IEEE Int'l Conference on Computer Vision and Pattern Recognition (CVPR 2014), Columbus, OH, USA, Jun. 2014, pp. 2577-2584.
[C26]
Remora: Sensing Resource Sharing Among Smartphone-based Body Sensor Networks [pdf]
Matthew Keally, Gang Zhou, Guoliang Xing, Jianxin Wu
In: Proc. IEEE/ACM International Symposium on Quality of Services (IWQoS 2013), Montreal, Canada, Jun. 2013, pp. 1-10.
[C.25]
Reduced Heteroscedasticity Linear Regression for Nystrom Approximation [pdf]
Hao Yang and Jianxin Wu
In: Proc. The 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013), Beijing, China, Aug. 2013, pp. 1841-1847.
[C24]
Salient Object Cutout Using Google Images [pdf]
Hongyuan Zhu, Jianfei Cai, Jianmin Zheng, Jianxin Wu, and Nadia Thalmann
In: Proc. 2013 IEEE International Symposium on Circuits and Systems (ISCAS 2013), Beijing, China, May 2013, pp. 905-908.
[C.23]
A New Network-based Algorithm for Human Group Activity Recognition in Videos [pdf]
Gaojian Li, Weiyao Lin, Sheng Zhang, Jianxin Wu, Yuanzhe Chen, and Hui Wei
In: Proc. 19th Conference on Multimedia Modeling, Huangshan (MMM 2013), Huangshan, China, Jan 2013, LNCS 7732, pp. 163-173.
[C.22]
Object Templates for Visual Place Categorization [pdf]
Hao Yang and Jianxin Wu
In: Proc. 11th Asian Conference on Computer Vision (ACCV 2012), Daejeon, Korea, Nov 2012, LNCS 7727, pp. 470-483.
[C.21]
Exclusive Visual Descriptor Quantization [pdf]
Yu Zhang, Jianxin Wu, and Weiyao Lin
In: Proc. 11th Asian Conference on Computer Vision (ACCV 2012), Daejeon, Korea, Nov 2012, LNCS 7724, pp. 408-421.
[C.20]
Key Instance Detection in Multi-Instance Learning [pdf]
Guoqing Liu, Jianxin Wu, and Zhi-Hua Zhou
In: Proc. 4th Asian Conference on Machine Learning (ACML 2012), Singapore, Singapore, Nov 2012, JMLR W&CP 25:253-268, 2012.
[C.19]
Practical Large Scale Classification with Additive Kernels [pdf]
Hao Yang and Jianxin Wu
In: Proc. 4th Asian Conference on Machine Learning (ACML 2012), Singapore, Singapore, Nov 2012, pp. JMLR W&CP 25:523-538, 2012.
[C.18]
A new heat-map-based algorithm for human group activity recognition [pdf]
Hang Chu, Weiyao Lin, Jianxin Wu, Xingtong Zhou, Yuanzhe Chen, Hongxiang Li
In: Proc. 20th ACM International Conference on Multimedia (MM 2012), Nara, Japan, Oct-Nov 2012, pp. 1069-1072. (short paper)
[C17]
Power Mean SVM for Large Scale Visual Classification [pdf][PmSVM software][PmSVM software mirror page]
Jianxin Wu
In: Proc. The IEEE Int'l Conference on Computer Vision and Pattern Recognition (CVPR 2012), Providence, RI, USA, Jun. 2012, pp. 2344-2351.
[C16]
Facial Expression Mapping based on Elastic and Muscle-Distribution-based Models [pdf]
Yihao Zhang, Weiyao Lin, Bin Sheng, Jianxin Wu, Hongxiang Li, Chongyang Zhang
In: Proc. The 2012 International Symposium on Circuits and Systems (ISCAS 2012), Seoul, Korea, May 2012, pp. 2685-2688.
[C.15]
PBN: Towards Practical Acitvity Recognition Using Smartphone-Based Body Sensor Networks [pdf]
Matthew Keally, Gang Zhou, Guoliang Xing, Jianxin Wu, Andrew Pyles
In: Proc. The 9th ACM Conference on Embedded Networked Sensor Systems (Sensys 2011), Seattle, WA, USA, Nov. 2011, pp. 246-259.
[C.14]
Probit Classifiers with a Generalized Gaussian Scale Mixture Prior [pdf]
Guoqing Liu, Jianxin Wu, and Suiping Zhou
In: Proc. The 22nd International Joint Conference on Artificial Intelligence (IJCAI 2011), Barcelona, Spain, July 2011, pp. 1372-1377.
[C13]
Real-Time Human Detection Using Contour Cues [pdf][C4 project page with source code][C4 mirror page]
Jianxin Wu, Christopher Geyer, and James M. Rehg
In: Proc. The 2011 IEEE Int'l Conference on Robotics and Automation (ICRA 2011), Shanghai, China, May 2011, pp. 860-867.
[C12]
Balance Support Vector Machines Locally Using the Structural Similarity Kernel
[pdf] [proejct page with source code]
Jianxin Wu
In: Proc. The 15th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2011), Shenzhen, China, May 2011, pp. I-(112-123).
[C11]
Exploiting Sensing Diversity for Confident Sensing in Wireless Sensor Networks [pdf]
Matthew Keally, Gang Zhou, Guoliang Xing, and Jianxin Wu
In: Proc. The 30th IEEE Int'l Conference on Computer Communications (INFOCOM 2011), Shanghai, China, Apr. 2011, pp. 1719-1727.
[C10]
A Fast Dual Method for HIK SVM Learning [pdf] [libHIK project page with source code][libHIK mirror page]
Jianxin Wu
In: Proc. The 11th European Conference on Computer Vision (ECCV 2010), Crete, Greece, Sep. 2010, LNCS vol. 6312, pp. 552-565.
[C9]
Visual Place Categorization: Problem, Dataset, and Algorithm [pdf][VPC dataset][VPC workshop]
Jianxin Wu, Henrik Christensen, and James M. Rehg
In: Proc. The 2009 IEEE/RSJ Int'l Conference on Intelligent Robots and Systems (IROS 2009), St. Louis, MO, USA, Oct. 2009, pp. 4763-4770.
[C8]
Beyond the Euclidean distance: Creating effective visual codebooks using the histogram intersection kernel
[pdf] [libHIK project page with source code][libHIK mirror page]
Jianxin Wu and James M. Rehg
In: Proc. The 12th International Conference on Computer Vision (ICCV 2009), Kyoto, Japan, Sep 2009, pp. 630-637.
[C7]
Where am I: Place instance and category recognition using spatial PACT [pdf] [project page with source code]
Jianxin Wu and James M. Rehg
In: Proc. The IEEE Int'l Conference on Computer Vision and Pattern Recognition (CVPR 2008), Anchorage, AS, USA, Jun. 2008, pp. 1-8.
[C6]
A Scalable Approach to Activity Recognition based on Object Use [pdf]
Jianxin Wu, Adebola Osuntogun, Tanzeem Choudhury, Matthai Philipose, and James M. Rehg
In: Proc. The 11th International Conference on Computer Vision (ICCV 2007), Rio de Janeiro, Brazil, Oct. 2007, pp. 1-8.
[C5]
Exploratory Under-Sampling for Class-Imbalance Learning [pdf][project page with source code]
Xu-Ying Liu, Jianxin Wu, and Zhi-Hua Zhou
In: Proc. The IEEE International Conference on Data Mining (ICDM 2006), Hong Kong, China, Dec. 2006, pp. 965-969.
[C.4]
Linear Asymmetric Classifier for Cascade Detectors [pdf][project page with source code]
Jianxin Wu, Matthew D. Mullin, and James M. Rehg
In: Proc. The 22nd International Conference on Machine Learning (ICML 2005), Bonn, Germany, Aug. 2005, pp. 993-1000.
[C3]
Learning a Rare Event Detection Cascade by Direct Feature Selection [pdf][project page with source code]
Jianxin Wu, James M. Rehg, and Matthew D. Mullin
In: Proc. Advances in Neural Information Processing Systems 16 (NIPS 2003), Vancouver, Canada, Dec. 2003, pp. 1523-1530.
[C.2]
Genetic algorithm based selective neural network ensemble [pdf][project page with source code]
Zhi-Hua Zhou, Jian-Xin Wu, Yuan Jiang, and Shi-Fu Chen
In: Proc. The 17th International Joint Conference on Artificial Intelligence (IJCAI 2001), Seattle, WA, USA, Aug. 2001, vol.2, pp. 797-802.
[C1]
Ensemble of GA based selective neural network ensembles [pdf][project page with source code]
Jian-Xin Wu, Zhi-Hua Zhou, and Zhao-Qian Chen
In: Proc. The 8th International Conference on Neural Information Processing (ICONIP 2001), Shanghai, China, Nov. 2001, vol. 3, pp. 1477-1482.
Visual Place Categorization
[pdf file, about 4.7M]
Ph.D. Dissertation in College of Computing, Georgia Institute of Technology, supervised by Dr. James M. Rehg
[W15]
(in Chinese) 基于深度特征的无监督图像检索研究综述
张皓;吴建鑫
计算机研究与发展, 2018, 55(9): 1829-1842.
[W14]
(in Chinese) 集成最大汇合：最大汇合时只有最大值有用吗?
张皓;吴建鑫
中国科学技术大学学报, 2017, 47(10): 799-807.
[W13]
Editorial of the Special Issue on Multi-instance Learning in Pattern Recognition and Vision
Jianxin Wu, Xiang Bai, Marco Loog, Fabio Roli, Zhi-Hua Zhou
Pattern Recognition, 71, 2017: 444-445.
[W12]
(in Chinese) 一种基于Hartigan-Wong和Lloyd的定性平衡聚类算法
周旺, 张晨麟, 吴建鑫
山东大学学报（工学版）, 2016, 46(5): 37-44.
[W11]
(in Chinese) 基于深度卷积特征的细粒度图像分类研究综述 [pdf]
罗建豪，吴建鑫
自动化学报，2017, 43(8): 1306-1318.
[W10]
Deep Bimodal Regression for Apparent Personality Analysis [pdf] [project page]
Chen-Lin Zhang, H Zhang, Xiu-Shen Wei, and Jianxin Wu
ChaLearn Looking at People: Workshop and Competitions (Apparent Personality Analysis track winner), in association with ECCV 2016
[W9]
Deep Spatial Pyramid Ensemble for Cultural Event Recognition [pdf]
Xiu-Shen Wei, Bin-Bin Gao, Jianxin Wu
ChaLearn Looking at People: Workshop and Competitions (LaP track 2 competition rank #2), in association with ICCV 2015
[W8]
Deep Label Distribution Learning for Apparent Age Estimation [pdf]
Xu Yang, Bin-Bin Gao, Chao Xing, Zeng-Wei Huo, Xiu-Shen Wei, Ying Zhou, Jianxin Wu, Xin Geng
ChaLearn Looking at People: Workshop and Competitions (LaP track 1 competition rank #4), in association with ICCV 2015
[W7]
(in Chinese) 一种基于近邻表示的聚类方法
周国兵，吴建鑫，周嵩
软件学报，2015, 26(11)： 2847-2855.
[W6]
Steerable Second Order Intensity Features for Pedestrian Detection
Sing Kuang Tan, Tat-Jen Cham, Jianxin Wu
In: Proc. The 3rd Asian Conference on Pattern Recognition, Kuala Lumpur, Malaysia, Nov. 2015.
[W5]
Additive Kernels and Explicit Embeddings for Large Scale Computer Vision Problems [Materials]
Tutorial in ECCV 2012, with Andrea Vedaldi (Univ. of Oxford, UK), Subhransu Maji (TTI Chicago, USA), and Florent Perronnin (Xerox Research Center Europe)
[W4]
Layout-expectation-based Model for Image Search Re-ranking [pdf]
International Workshop on Emerging Multimedia Systems and Applications, in conjunction with ICME 2012.
[W3]
Histogram Intersection Kernel Learning for Multimedia Applications [pdf]
Tutorial in the 2010 Pacific-Rim Conference on Multimedia, Sept. 21, 2010, Shanghai.
[W2]
Towards the Optimal Training of Cascades of Boosted Ensembles [SpringerLink page
S. Charles Brubaker, Jianxin Wu, Jie Sun, Matthew D. Mullin, and James M. Rehg
Toward Category-Level Object Recognition 2006 (LNCS 4170): pages 301-320.
[W1]
Learning a Rare Event Detection Cascade by Direct Feature Selection
Jianxin Wu, James M. Rehg, and Matthew D. Mullin
SCTV 2003, in conjunction with ICCV 2003.