Xiu-Shen WEI （魏秀参）– Papers

(* denotes the corresponding author.)

Journal Articles

• 属性知识自反绎下的半监督表示学习 (in Chinese).
  Y. Shen, X. Sun, H.-Y. Xu, and X.-S. Wei*.
  SCIENTIA SINICA Informationis (中国科学：信息科学), in press.

• Negatives Make A Positive: An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning.
  X.-S. Wei, H.-Y. Xu, Z. Yang, C.-L. Duan, and Y. Peng.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), in press.

• Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval.
  X.-S. Wei, Y. Shen, X. Sun, P. Wang, and Y. Peng.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023, 45(11): 13904-13920.

• Contextualizing Meta-Learning via Learning to Decompose.
  H.-J. Ye, D.-W. Zhou, L. Hong, Z. Li, X.-S. Wei, and D.-C. Zhan.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), in press.

• Task-Specific Part Discovery for Fine-Grained Few-Shot Classification.
  Y. Wei, and X.-S. Wei*.
  Machine Intelligence Research (MIR), in press.

• CAT: A Coarse-to-fine Attention Tree for Semantic Change Detection.
  X.-S. Wei, Y.-Y. Xu, C.-L. Zhang, G.-S. Xia, and Y. Peng.
  Visual Intelligence (VI), 2023, 1: 3.

• Open-set object detection based on annular prototype space optimization (in Chinese).
  X. Sun, Y. Shen, X.-S. Wei*, and P. An.
  Journal of Image and Graphics (中国图象图形学报), 2023, 28(9): 2719-2732.

• Prototype Learning for Automatic Check-Out.
  H. Chen, X.-S. Wei*, and L. Xiao.
  IEEE Transactions on Multimedia (TMM), 2023, 25: 9147-9160.

• RPC: A Large-Scale and Fine-Grained Retail Product Checkout Dataset.
  X.-S. Wei*, Q. Cui, L. Yang, P. Wang, L. Liu, and J. Yang.
  SCIENCE CHINA Information Sciences (中国科学：信息科学), 2022, 65(9): 197101.
  [Chinese introduction] [project page]

• Multi-Instance Learning with Incremental Classes (in Chinese).
  X.-S. Wei, S.-L. Xu, P. An, and J. Yang.
  Journal of Computer Research and Development (计算机研究与发展), 2022, 59(8): 1723-1731.

• Fine-Grained Image Analysis with Deep Learning: A Survey.
  

  (This work was the highly cited paper by ESI, which received enough citations to place it in the top 1% of its academic field.)

  (入选首届江苏自然科学百篇优秀学术成果！[新闻报道])

  X.-S. Wei*, Y.-Z. Song, O. Mac Aodha, J. Wu, Y. Peng, J. Tang, J. Yang, and S. Belongie.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022, 44(12): 8927-8948.

• Learning Graph Convolutional Networks for Multi-Label Recognition and Applications.
  

  (This work was the highly cited paper by ESI, which received enough citations to place it in the top 1% of its academic field.)

  Z. Chen, X.-S. Wei*, P. Wang, and Y. Guo.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023, 45(6): 6969-6983.

• Webly-Supervised Fine-Grained Image Recognition (in Chinese).
  X.-S. Wei, Y.-Y. Xu, and J. Yang.
  Journal of Image and Graphics (中国图象图形学报), 2022, 27(7): 2057-2077.

• QBox: Partial Transfer Learning with Active Querying for Object Detection.
  Y.-P. Tang, X.-S. Wei, B. Zhao, and S.-J. Huang.
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023, 34(6): 3058-3070.

• Prototype-based Classifier Learning for Long-Tailed Visual Recognition.
  X.-S. Wei, S.-L. Xu, H. Chen, L. Xiao, and Y. Peng.
  SCIENCE CHINA Information Sciences (中国科学：信息科学), 2022, 65(6): 160105.
  [Chinese introduction]

• Self-Supervised Multi-Category Counting Networks for Automatic Check-Out.
  H. Chen, Y. Zhou, J. Li, X.-S. Wei*, and L. Xiao.
  IEEE Transactions on Image Processing (TIP), 2022, 31: 3004-3016.

• Delving Deep into Spatial Pooling for Squeeze-and-Excitation Networks.
  X. Jin, Y. Xie, X.-S. Wei*, B.-R. Zhao, Z.-M. Chen, and X. Tan.
  Pattern Recognition, 2022, 121.

• A Lightweight Encoder-Decoder Path for Deep Residual Networks.
  X. Jin, Y. Xie, X.-S. Wei*, B.-R. Zhao, Y.-S. Zhang, X. Tan, and Y. Yu.
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022, 33(2): 866-878.
  [code]

• Multi-Instance Learning with Emerging Novel Class.
  X.-S. Wei, H.-J. Ye, X. Mu, J. Wu, C. Shen, and Z.-H. Zhou.
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021, 33(5): 2109-2120.
  [code & data]

• Disentangling, Embedding and Ranking Label Cues for Multi-Label Image Recognition.
  Z.-M. Chen, Q. Cui, X.-S. Wei*, X. Jin, and Y. Guo.
  IEEE Transactions on Multimedia (TMM), 2020, 23: 1827-1840.

• Bi-Modal Progressive Mask Attention for Fine-Grained Recognition.
  K. Song, X.-S. Wei*, X. Shu, R.-J. Song, and J. Lu.
  IEEE Transactions on Image Processing (TIP), 2020, 29: 7006-7018.

• Structure-Aware Human Pose Estimation with Graph Convolutional Networks.
  Y. Bin, Z.-M. Chen, X.-S. Wei*, X. Chen, C. Gao, and N. Sang.
  Pattern Recognition, 2020, 106.

• Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization.
  Y. Chen, C. Shen, H. Chen, X.-S. Wei, L. Liu, and J. Yang.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020, 42(7): 1654-1669.

• Piecewise Classifier Mappings: Learning Fine-Grained Learners for Novel Categories with Few Examples.
  X.-S. Wei, P. Wang, L. Liu, C. Shen, and J. Wu.
  IEEE Transactions on Image Processing (TIP), 2019, 28(12): 6116-6125.

• Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transformation.
  X.-S. Wei, C.-L. Zhang, J. Wu, C. Shen, and Z.-H. Zhou.
  Pattern Recognition, 2019, 88:113-126.
  [project page]

• Resource Constrained Deep Learning: Challenges and Practices (in Chinese).
  J. Wu, B.-B. Gao, X.-S. Wei, and J.-H. Luo.
  SCIENCE CHINA Information Sciences (中国科学：信息科学), 2018, 48(5): 501-510.

• Deep Bimodal Regression of Personality Traits from Short Video Sequences.
  X.-S. Wei, C.-L. Zhang, H. Zhang, and J. Wu.
  IEEE Transactions on Affective Computing (TAC), 2018, 9(3): 303-315.
  [project page]

• Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Bird Species Categorization.
  X.-S. Wei, C.-W. Xie, J. Wu, and C. Shen.
  Pattern Recognition, 2018, 76:704-714.
  [project page]

• Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval.
  

  (This work was the highly cited paper by ESI, which received enough citations to place it in the top 1% of its academic field.)

  X.-S. Wei, J.-H. Luo, J. Wu, and Z.-H. Zhou.
  IEEE Transactions on Image Processing (TIP), 2017, 26(6): 2868-2881.
  [project page]

• Scalable Algorithms for Multi-Instance Learning.
  X.-S. Wei, J. Wu, and Z.-H. Zhou.
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2017, 28(4): 975-987.
  [project page]

• An Empirical Study on Image Bag Generators for Multi-Instance Learning.
  X.-S. Wei, and Z.-H. Zhou.
  Machine Learning, 2016, 105(2): 155-198.
  [slide] [code]

• Weakly Supervised Fine-Grained Categorization with Part-Based Image Representation.
  Y. Zhang, X.-S. Wei, J. Wu, J. Cai, J. Lu, V.-A. Nguyen, and M. N. Do.
  IEEE Transactions on Image Processing (TIP), 2016, 25(4): 1713-1725.

Conference Papers

• An Asymmetric Augmented Self-Supervised Learning Method for Unsupervised Fine-Grained Image Hashing.
  F. Hu, C.-L. Zhang, J. Guo, X.-S. Wei*, L. Zhao, A. Xu, and L. Gao.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR’24), Seattle, WA, 2024, pp. xx-xx.

• Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels.
  S.-L. Xu, Y. Sun, F. Zhang, A. Xu, X.-S. Wei*, and Y. Yang.
  Neural Information Processing Systems (NeurIPS’23), New Orleans, 2023, pp. xx-xx. (Acceptance Rates: 3222/12343=26.1%)

• Hawkeye: A PyTorch-based Library for Fine-Grained Image Recognition with Deep Learning.
  J. He, Y. Shen, X.-S. Wei*, and Y. Wu.
  ACM Multimedia Conference (ACM MM’23), Ottawa, Canada, 2023, pp. 9656-9659.
  [project page]

• Equiangular Basis Vectors.
  

  (This work was the winner solution of the 2022 DIGIX global AI challenge.)

  Y. Shen, X. Sun, and X.-S. Wei*.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR’23), Vancouver, Canada, 2023, pp. 11755-11765. (Acceptance Rates: 2360/9155=25.8%)
  [supplementary materials] [code]

• An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning. (Spotlight presentation)
  X.-S. Wei, H.-Y. Xu, F. Zhang, Y. Peng, and W. Zhou.
  Neural Information Processing Systems (NeurIPS’22), New Orleans, 2022, pp. 14489-14500. (Spotlight Presentation Acceptance Rates: 523/10411=5.0%)

• SEMICON: A Learning-to-hash Solution for Large-Scale Fine-Grained Image Retrieval.
  Y. Shen, X. Sun, X.-S. Wei*, Q.-Y. Jiang, and J. Yang.
  European Conference on Computer Vision (ECCV’22), Tel Aviv, Israel, 2022, pp. 531-548. (Acceptance Rates: 1650/5803=28%)

• Automatic Check-Out via Prototype-based Classifier Learning from Single-Product Exemplars.
  H. Chen, X.-S. Wei*, F. Zhang, Y. Shen, H. Xu, and L. Xiao.
  European Conference on Computer Vision (ECCV’22), Tel Aviv, Israel, 2022, pp. 277-293. (Acceptance Rates: 1650/5803=28%)

• Webly-Supervised Fine-Grained Recognition with Partial Label Learning.
  Y.-Y. Xu, Y. Shen, X.-S. Wei*, and J. Yang.
  International Joint Conference on Artificial Intelligence (IJCAI’22), Vienna, Australia, 2022, pp. 1502-1508. (Acceptance Rates: 681/4535=15.02%)

• Part-Level Filter Banks for Few-Shot Fine-Grained Image Recognition.
  S.-L. Xu, X.-S. Wei*, and J. Yang.
  China Conference on Data Mining (CCDM’22), Guilin, China, 2022.

• A Channel Mix Method for Fine-Grained Cross-Modal Retrieval.
  Y. Shen, X. Sun, X.-S. Wei*, H. Hu, and Z. Chen.
  IEEE Conference on on Multimedia and Expo (ICME’22), Taipei, Taiwan, 2022, DOI: 10.1109/ICME52920.2022.9859609.

• Relieving Long-tailed Instance Segmentation via Pairwise Class Balance.
  Y.-Y. He, P. Zhang, X.-S. Wei, X. Zhang, and J. Sun.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR’22), New Orleans, LA, 2022, pp. 7000-7009. (Acceptance Rates: 2067/8161=25%)

• Dual Attention Networks for Few-Shot Fine-Grained Recognition. (Oral presentation)
  S.-L. Xu, F. Zhang, X.-S. Wei*, and J. Wang.
  AAAI Conference on Artificial Intelligence (AAAI’22), Vancouver, BC, Canada, 2022, pp. 2911-2919. (Oral Presentation Acceptance Rates: 384/9020=4%)

• A-Net: Learning Attribute-Aware Hash Codes for Large-Scale Fine-Grained Image Retrieval. (Spotlight presentation)
  X.-S. Wei, Y. Shen, X. Sun, H.-J. Ye, and J. Yang.
  Neural Information Processing Systems (NeurIPS’21), Virtual, 2021, pp. 5720-5730. (Spotlight Presentation Acceptance Rates: 282/9122=3.1%)

• Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach.
  Z. Sun, Y. Yao, X.-S. Wei*, Y. Zhang, F. Shen, J. Wu, J. Zhang, and H. T. Shen.
  IEEE International Conference on Computer Vision (ICCV’21), Virtual, 2021, pp. 10602-10611.

• Distilling Virtual Examples for Long-Tailed Recognition.
  Y.-Y. He, J. Wu, and X.-S. Wei.
  IEEE International Conference on Computer Vision (ICCV’21), Virtual, 2021, pp. 235-244.

• Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification.
  P. Wang, K. Han, X.-S. Wei, L. Zhang, and L. Wang.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR’21), Virtual, 2021, pp. 943-952. (Acceptance Rates: 1663/7500=22%)

• Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural Networks.
  Y. Zhang, X.-S. Wei*, B. Zhou, and J. Wu.
  AAAI Conference on Artificial Intelligence (AAAI’21), Virtual, 2021, pp. 3447-3455. (Acceptance Rates: 1692/7911=21%)
  [code]

• CRSSC: Salvage Reusable Samples from Noisy Data for Robust Learning. (Oral presentation)
  Z. Sun, X.-S. Hua, Y. Yao, X.-S. Wei, G. Hu, and J. Zhang.
  ACM Multimedia Conference (ACM MM’20), Virtual, 2020, pp. 92-101. (Oral Presentation Acceptance Rates: 153/1698=9%)

• PyRetri: A PyTorch-based Library for Unsupervised Image Retrieval by Deep Convolutional Neural Networks.
  B. Hu, R.-J. Song, X.-S. Wei*, Y. Yao, X.-S. Hua, and Y. Liu.
  ACM Multimedia Conference (ACM MM’20), Virtual, 2020, pp. 4461-4464.
  [project page]

• ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval. (Oral presentation)
  Q. Cui, Q.-Y. Jiang, X.-S. Wei*, W.-J. Li, and O. Yoshie.
  European Conference on Computer Vision (ECCV’20), Virtual, 2020, pp. 189-205. (Oral Presentation Acceptance Rates: 104/5025=2%)

• Hierarchical Context Embedding for Region-based Object Detection.
  Z.-M. Chen, X. Jin, B. Zhao, X.-S. Wei*, and Y. Guo.
  European Conference on Computer Vision (ECCV’20), Virtual, 2020, pp. 633-648. (Acceptance Rates: 1361/5025=27%)

• BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition. (Oral presentation)
  

  (This work was the winner solution of the iNaturalist 2019 global competition.)

  B. Zhou, Q. Cui, X.-S. Wei*, and Z.-M. Chen.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR’20), Virtual, 2020, pp. 9719-9728. (Oral Presentation Acceptance Rates: 335/6656=5%)
  [supplementary materials] [poster] [code]

• Exploring Categorical Regularization for Domain Adaptive Object Detection.
  C. Xu, X. Zhao, X. Jin, and X.-S. Wei*.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR’20), Virtual, 2020, pp. 11724-11733. (Acceptance Rates: 1470/6656=22%)
  [supplementary materials] [code]

• An Adversarial Domain Adaptation Network for Cross-Domain Fine-Grained Recognition.
  Y. Wang, R.-J. Song, X.-S. Wei, and L. Zhang.
  IEEE Winter Conference on Applications of Computer Vision (WACV’20), Snowmass Village, CO, 2020, pp. 1228-1236.
  [project page] [presentation]

• Multi-Label Image Recognition with joint Class-aware Map Disentangling and Label Correlation Embedding. (Oral presentation)
  Z.-M. Chen, X.-S. Wei*, X. Jin, and Y. Guo.
  IEEE Conference on on Multimedia and Expo (ICME’19), Shanghai, China, 2019, pp. 622-627.

• Multi-Label Image Recognition with Graph Convolutional Networks.
  Z.-M. Chen, X.-S. Wei*, P. Wang, and Y. Guo.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR’19), Long Beach, CA, 2019, pp. 5177-5186. (Acceptance Rates: 1299/5165=25.15%)
  [slides] [code]

• Coarse-to-Fine: A RNN-based Hierarchical Attention Model for Vehicle Re-Identification.
  X.-S. Wei, C.-L. Zhang, L. Liu, C. Shen, and J. Wu.
  Asian Conference on Computer Vision (ACCV’18), Perth, Australia, 2018, pp. 575-591. (Acceptance Rates: 274/979=27.98%)
  [poster] [code]

• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation.
  Y. Chen, C. Shen, X.-S. Wei, L. Liu, and J. Yang.
  IEEE International Conference on Computer Vision (ICCV’17), Venice, Italy, 2017, pp. 1212-1221.

• Deep Descriptor Transforming for Image Co-Localization.
  X.-S. Wei, C.-L. Zhang, Y. Li, C.-W. Xie, J. Wu, C. Shen, and Z.-H. Zhou.
  International Joint Conference on Artificial Intelligence (IJCAI’17), Melbourne, Australia, 2017, pp. 3048-3054. (Acceptance Rates: 660/2540=25.98%)
  [slides] [poster] [code]

• In Defense of Fully Connected Layers in Visual Representation Transfer.
  C.-L. Zhang, J.-H. Luo, X.-S. Wei, and J. Wu.
  Pacific-Rim Conference on Multimedia (PCM’17), Harbin, China, 2017, pp. 807-817.

• Deep Spatial Pyramid Ensemble for Cultural Event Recognition.
  X.-S. Wei, B.-B. Gao, and J. Wu.
  IEEE International Conference on Computer Vision (ICCV’15) Workshops, Santiago, Chile, 2015, pp. 280-286.
  [slides]

• Deep Label Distribution Learning for Apparent Age Estimation.
  X. Yang, B.-B. Gao, C. Xing, Z.-W. Huo, X.-S. Wei, Y. Zhou, J. Wu, and X. Geng.
  IEEE International Conference on Computer Vision (ICCV’15) Workshops, Santiago, Chile, 2015, pp. 344-350.
  [slides]

• Scalable Multi-Instance Learning.
  X.-S. Wei, J. Wu, and Z.-H. Zhou.
  IEEE International Conference on Data Mining (ICDM’14), Shenzhen, China, 2014, pp.1037-1042. (Acceptance Rates: 142/727=19.53%)
  [project page]

Interdisciplinarity

• Leveraging DNA-based Nanostructures for Advanced Error Detection and Correction in Data Communication. (Cover Article)
  R. Gao, X.-S. Wei*, Z. Chen, A. Xie, and W. Dong.
  ACS Nano, 2023, 17(18): 18055-18061.

Technical Reports

• RPC: A Large-Scale Retail Product Checkout Dataset.
  

  (The largest fine-grained product dataset so far for retail scenarios.)

  X.-S. Wei, Q. Cui, L. Yang, P. Wang, and L. Liu.
  arXiv:1901.07249, 2019.
  [project page]

• Deep Spatial Pyramid: The Devil is Once Again in the Details.
  B.-B. Gao, X.-S. Wei, J. Wu, and W. Lin.
  arXiv:1504.05277v2, 2015.

Other Papers

• 新工科背景下深度学习理论实践一体化课程与教材建设研究.
  魏秀参，肖亮.
  计算机教育, in press.

• 长尾分布图像识别：途径与进展.
  魏秀参.
  中国基础科学, 2023, 5:50-57.

• Preface of Special Section on Self-Learning with Deep Neural Networks.
  M.-L. Zhang, X.-S. Wei, and G. Huang.
  Journal of Computer Science and Technology, 2022, 37 (3): 505-506.

• 基于深度哈希的大规模细粒度图像检索.
  魏秀参，沈阳.
  中国计算机学会计算机视觉专委会简报, 2021, 1, 14-15.

• 细粒度图像识别研究进展.
  魏秀参，陈昊.
  中国自动化学会模式识别与机器智能专业委员会通讯, 2020, 3(11), 61-70.

• 针对长尾数据分布的深度视觉识别.
  魏秀参.
  中国人工智能学会通讯, 2020, 10(5), 26-30.

• 计算机视觉的“夏日联欢”——CVPR 2018.
  魏秀参，金鑫.
  中国计算机学会通讯, 2018, 14(7), 73-75.

• 二次集成学习在医疗数据挖掘中的应用.
  魏秀参，慕鑫，杨杨.
  计算机科学与探索, 2014, 8(9), 1113-1119.