Publications sorted by topic
Contexual similarity and similarity fusing for re-ranking and its applications to shape retrieval, image retrieval, and visual tracking
- S. Bai, S. Zhang, X. Bai, Z. Zhang, Q. Tian. Smooth Neighborhood Structure Mining on Multiple Affinity Graphs with Applications to Context-sensitive Similarity. European Conf. on Computer Vision (ECCV), 2016.
- Song Bai, Xiang Bai. Sparse Contextual Activation for Efficient Visual Re-ranking. IEEE Trans. on Image Proc. (TIP), 25(3): 1056-1069, 2016.[PDF][CODE]
- Yu Zhou, Xiang Bai, Wenyu Liu, Longin Jan Latecki.Similarity Fusion for Visual Tracking.International Journal of Computer Vision (IJCV),118(3),337-363, 2016.[PDF]
- Xiang Bai, Song Bai, Xinggang Wang.Beyond Diffusion Process: Neighbor Set Similarity for Fast Re-Ranking.Information Science (IS),325(20),pp.342�C354, 2015.[PDF]
- Xingwei Yang, Xiang Bai, Suzan Koknar-Tezel, Longin Jan Latecki. Densifying Distance Spaces for Shape and Image Retrieval. Journal of Mathematical Imaging and Vision (JMIV) 46(1): 12-28, 2013.
- Yu Zhou, Xiang Bai, Wenyu Liu, and Longin Jan Latecki. Fusion with Diffusion for Robust Visual Tracking. Neural Information Processing Systems (NIPS), 2012. [PDF]
- Xiang Bai, Bo Wang, Cong Yao, Wenyu Liu, and Zhuowen Tu. Co-Transduction for Shape Retrieval.IEEE Transactions on Image Processing (TIP), 2012.[PDF] [Code]
- Jingyan Wang, Yongping Li, Xiang Bai, Ying Zhang, Chao Wang, Ning Tang.Learning context-sensitive similarity by shortest path propagation.Pattern Recognition (PR), 2011, 44(10-11): 2367-2374.
- X. Bai, X. Yang, L.Latecki, W. Liu, and Z.
Tu. Learning Context-Sensitive Shape Similarity by Graph Transduction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2010, 32(5):
861-874 . [PDF](code is in "Co-Transduction")
- Xiang Bai, Bo Wang, Xinggang Wang, Wenyu Liu, and Zhuowen Tu. Co-Transduction for Shape Retrieval. European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.[PDF]
- Xingwei Yang, Xiang Bai, Longin Jan Latecki, and Zhuowen Tu. Improving Shape Retrieval by Learning Graph Transduction [PDF]European Conference on Computer Vision (ECCV), Marseille, France, October 2008.
Text detection and recognition in the wild
- M. Liao, B. Shi, X. Bai, X. Wang, W. Liu. TextBoxes: A Fast Text Detector with a Single Deep Neural Network. The 31st AAAI Conference on Artificial Intelligence (AAAI), San Francisco, California, 2017. [PDF][code]
- Baoguang Shi, Xiang Bai, Cong Yao. An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), to appear. [CODE][Music Score Recognition Datasets]
- X. Bai, B. Shi, C. Zhang, X. Cai, L. Qi. Text/non-text image classification in the wild with convolutional neural networks. Pattern Recognition (PR), accepted.[pdf]
- C. Yao, X. Bai, N. Sang, X. Zhou, S. Zhou, Z. Cao. Scene Text Detection Via Holistic, Multi-Channel Prediction. arXiv:1606.09002, 2016.
- B. Shi, X. Wang, P. Lv, C. Yao, X. Bai. Robust scene text recognition with automatic rectification. IEEE Conf. on Computer Vis. & Pattern Recog. (CVPR), 2016.[pdf]
- Z. Zhang, C. Zhang, W. Shen, C. Yao, W. Liu, X. Bai. Multi-oriented text detection with fully convolutional networks. IEEE Conf. on Computer Vision and Pattern Recog. (CVPR), 2016. [PDF][code]
- Xiang Bai, Cong Yao, Wenyu Liu. Strokelets: A Learned Multi-Scale Mid-Level Representation for Scene Text Recognition. IEEE Transations on Image Proc.(TIP), 25(6),2789-2802, 2016.[PDF][CODE][Readme]
- Baoguang Shi, Xiang Bai, Cong Yao. Script Identification in the Wild via Discriminative Convolutional Neural Network, Pattern Recognition (PR), 52: 448-458, 2016. [PDF][Project Page & Datasets]
- Yingying Zhu, Cong Yao, Xiang Bai. Scene Text Detection and Recognition: Recent Advances and Future Trends. Frontier of Computer Science (FCS), 10(1): 19�C36, 2016. [PDF] (Invited paper)
- Z. Zhang, W. Shen, C. Yao, X. Bai. Symmetry-based Text Line Detection in Natural Scenes. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, June 2015.[PDF][CODE][Executable Software]
- B. Shi, C. Yao, C. Zhang, X. Guo, F. Huang, and X. Bai. Automatic Script Identification in the Wild. [PDF] International Conference on Document Analysis and Recognition (ICDAR), 2015.(Oral presentation)[Project Page&Dataset]
- C. Zhang, C. Yao, B. Shi, X. Bai. Automatic Discrimination of Text and Non-Text Natural Images.[PDF] International Conference on Document Analysis and Recognition (ICDAR), 2015. (Oral presentation)[Project Page&Dataset]
- Cong Yao, Xiang Bai, Baoguang Shi, Wenyu Liu. Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, USA, June 2014. [PDF][CODE][Readme]
- Cong Yao, Xiang Bai, Wenyu Liu. A Unified Framework for Multi-Oriented Text Detection and Recognition. IEEE Transactions on Image Processing (TIP), 23(11): 4737 - 4749, 2014. [PDF][HUST-TR 400 Dataset]
- ong Yao, Xin Zhang, Xiang Bai*, Wenyu Liu, Yi Ma, Zhuowen Tu. Rotation-invariant Features for Multi-oriented Text Detection in Natural Images. PLoS ONE 8(8), 2013, e70173. [PDF]
- Cong Yao, Xiang Bai, Wenyu Liu, Yi Ma, and Zhuowen Tu. Detecting Texts of Arbitrary Orientations in Natural Images. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
Providence, Rhode Island, 2012.[PDF] MSRA-TD 500 Dataset
Object detection, recognition, discovery, and Image Classification\labeling
- Song Bai, Xiang Bai, Wenyu Liu. Multiple Stage Residual Model for Image Classification and Vector Compression. IEEE Transations on Multimedia (TMM), 18(7): 1351-1362 2016. [PDF]
- X. Wang, Z. Zhu, C. Yao, X. Bai. Relaxed Multiple-Instance SVM with Application to Object Discovery.International Conference on Computer Vision (ICCV),2015. [PDF][CODE]
- X. Wang, Z. Zhang, Y. Ma, X. Bai, W. Liu, Z. Tu. Robust Subspace Discovery via Relaxed Rank Minimization,Neural Computation (NC), Vol. 26,No. 3 April 2014, Pages 611-635. [PDF][Code]
- Cong Yao, Xiang Bai, Wenyu Liu, Login Jan Latecki. Human Detection using Learned Part Alphabet and Pose Dictionary. European Conference on Computer Vision (ECCV), Zurich, Switzerland, September 2014.[PDF]
- Song Bai, Xinggang Wang, Cong Yao, Xiang Bai. Multiple Stage Residual Model for Accurate
Image Classication.Asian Conference on Computer Vision (ACCV), 2014. [PDF]
- Weichao Qiu, Xinggang Wang, Xiang Bai, Alan Yuille, Zhuowen Tu. Scale-space SIFT Flow. [PDF] IEEE Winter Conference on Applications of Computer Vision (WACV), Steamboat Springs CO, March, 2014.
- Xinggang Wang, Baoyuan Wang, Xiang Bai, Wenyu Liu, Zhuowen Tu. Max-Margin Multiple-Instance Dictionary Learning. International Conference on Machine Learning (ICML), 2013. [PDF][Code]
- Xinggang Wang, Zhengdong Zhang, Yi Ma, Xiang Bai, Wenyu Liu, and
Zhuowen Tu. One-Class Multiple Instance Learning via Robust PCA for Common Object Discovery. The 11th Asian Conference on Computer Vision (ACCV), November 5 - 9, 2012.[PDF]
- Yingying Zhu, Xinggang Wang, Cong Yao, Xiang Bai.Traffic Sign Classification Using Two-Layer Image Representation. International Conference on Image Processing (ICIP), 2013.
- Xinggang Wang, Xiang Bai, Wenyu Liu, and Longin Jan Latecki. Feature Context for Image Classification and Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
Colorado Springs, Colorado, 2011.[PDF][Code]
- Z. Tu and X. Bai. Auto-Context and Its Application to High-Level Vision Tasks and 3D Brain Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2010, 32(10):
1744-1757. [PDF]
2D/3D shape matching, retrieval, classification, clustering
- S. Bai, X. Bai, Z. Zhou, Z. Zhang, L.J. Latecki. GIFT: A real-time and scalable 3D shape search engine. IEEE Conf. on Compututer Vision and Pattern Recog. (CVPR), 2016.[PDF][CODE]
- Xinggang Wang, Xiong Duan, Xiang Bai. Deep Sketch Feature for Cross-domain Image Retrieval. Neurocomputing, accepted. [PDF] [CODE]
- Xiang Bai, Song Bai, Zhuotun Zhu, Longin Latecki. 3D Shape Matching via Two Layer Coding. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 37(12): 2361-2373, 2015.[PDF]
- Baoguang Shi, Song Bai, Zhichao Zhou, Xiang Bai. DeepPano: Deep Panoramic Representation for 3D Shape Recognition. IEEE Signal Processing Letters (SPL) , 22(12): 2339-2343, 2015.[PDF]
- Song Bai, Xiang Bai,Wenyu Liu, Fabio Roli. Neural Shape Codes for 3D Model Retrieval. Pattern Recognition Letters (PRL), 65(11): 15-21, 2015. [PDF]
- Zhuotun Zhu, Xinggang Wang, Song Bai, Cong Yao, Xiang Bai. Deep Learning Representation using Autoencoder for 3D Shape Retrieval. Neurocomputing, 204: 41-50, 2016.
- Zhuotun Zhu, Xinggang Wang, Song Bai, Cong Yao, Xiang Bai. Deep Learning Representation using Autoencoder
for 3D Shape Retrieval, ISPAC, 2014.
- Xiang Bai, Cong Rao, Xinggang Wang. Shape Vocabulary: A Robust and Efficient Shape Representation for Shape Matching. IEEE Transactions on Image Processing (TIP), 23(9):3935-3949, 2014. [PDF][CODE]
- Song Bai, Xinggang Wang, Xiang Bai. Aggregating Contour Fragments for shape classification, International Conference on Image Processing (ICIP), 2014.
- Wei Shen, Xinggang Wang, Cong Yao, Xiang Bai. Shape Recognition by Combining Contour and Skeleton into a Mid-Level Representation, China Conference on Pattern Recognition (CCPR), 2014.
- X. Wang, B. Feng, X. Bai, W. Liu, L.J. Latecki. Bag of Contour Fragments for Robust Shape Classification.Pattern Recognition (PR), 47(6): 2116-2125, 2014. [PDF][Code]
- Yu Zhou, Juntao Liu, Xiang Bai. Research and Perspective on Shape Matching. ��״ƥ���о���չ��. Acta Automatica Sinica, 2012. [pdf]
- Junwei Wang, Xiang Bai*, Xinge You, Wenyu Liu, and Longin Jan Latecki. Shape Matching and Classification Using Height Functions. Pattern Recognition Letters (PRL), 2012, 33(2): 134-143. [PDF] [Code]
- Bo Wang, Wei Shen, Wen-Yu Liu, Xin-Ge You, and Xiang Bai. Shape Classification Using Tree-Unions. International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, August
2010. [PDF]
- Xiang Bai, Wenyu Liu, and Zhuowen Tu. Integrating Contour and Skeleton for Shape Classification [PDF][Animal Dataset]International Workshop on NORDIA (in conjunction with ICCV2009), Kyoto, Japan, September-October
2009.
- Xiang Bai, Xingwei Yang, and Longin Jan Latecki. Detection and Recognition of Contour Parts Based on Shape Similarity. Pattern Recognition (PR), 2008, 41(7): 2189-2199.[PDF]
- Xiang Bai, Xingwei Yang, De-Guang Yu, and Longin Jan Latecki. Skeleton-Based Shape Classification Using Path Similarity. International J. of Pattern Recognition and Artificial Intelligence (IJPRAI),
2008, 22(4): 733-746. [PDF]
Contour/symmetry detection and grouping, shape-based object detection
- W. Shen, K. Zhao, Y. Jiang, Y. Wang, Z. Zhang, X. Bai. Object skeleton extraction in natural images by fusing scale-associated deep side outputs. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016.[pdf][Supplementary Material][CODE]
- W. Shen, X. Wang, Y. Wang, X. Bai, Z. Zhang. DeepContour: A Deep Convolutional Feature Learned by Positive-sharing Loss for Contour Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, June 2015 . [PDF] [CODE] (Pre-computed Result on BSDS500) (PR-curve Data)
- Wei Shen, Xiang Bai, Zihao Hu, Zhijiang Zhang.
Multiple Instance Subspace Learning via Partial Random Projection Tree for Local Reflection Symmetry in Natural Images. Pattern Recognition (PR), accepted.[PDF]
- Xinggang Wang, Xiang Bai, Tianyang Ma, Wenyu Liu, and Longin Jan
Latecki. Fan Shape Model for Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
Providence, Rhode Island, 2012.[PDF][Code]
- Xinggang Wang, Xiang Bai, Xingwei Yang, Wenyu Liu, and L.J.
Latecki.Maximal Cliques that Satisfy Hard Constraints with Application to Deformable Object
Model Learning. Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS),
Granada, Spain, December 2011.[PDF]
- Bo Wang, Xiang Bai, Xinggang Wang, Wenyu Liu, and Zhuowen Tu. Object Recognition Using Junctions.European Conference on Computer Vision (ECCV), Crete, Greece, September 2010. [PDF]
- Xiang Bai, Quannan Li, Longin Jan Latecki, Wenyu Liu, and Zhuowen
Tu. Shape Band: A Deformable Object Detection Approach [PDF] IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
Miami, Florida, USA, June 2009.
- Xiang Bai, Xinggang Wang, Longin Jan Latecki, Wenyu Liu, and Zhuowen
Tu. Active Skeleton for Non-rigid Object Detection [PDF][Code] International Conference on Computer Vision (ICCV), Kyoto, Japan, September-October
2009.
- Longin Jan Latecki, ChengEn Lu, Marc Sobel, and Xiang Bai. Multiscale Random Fields with Application to Contour Grouping [PDF]Annual Conference on Neural Information Processing Syestems (NIPS),
Vancouver, British Columbia, Canada, 2008.
Skeletonization, skeleton Pruning, skeleton-based shape matching
- W. Shen, K. Zhao, Y. Jiang, Y. Wang, Z. Zhang, X. Bai. Object skeleton extraction in natural images by fusing scale-associated deep side outputs. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016.[pdf][Supplementary Material][CODE]
- Wei Shen, Xiang Bai, Xingwei Yang, Longin Jan Latecki. Skeleton pruning as trade-off between skeleton simplicity and reconstruction error. SCIENCE CHINA Information Science , April 2013, Vol. 56, No: 1�C18. [PDF] [Code]
- Wei Shen, Yan Wang, Xiang Bai, Hongyuan Wang, Longin Jan Latecki. Shape clustering: Common structure discovery. Pattern Recognition (PR) 46 (2013) 539�C550. [PDF][Code]
- W. Liu, H. Jiang, X. Bai, G. Tan, C. Wang, W. Liu, K. Cai. Distance Transform-based Skeleton Extraction and Its Applications in Sensor Networks. IEEE Transactions on Parallel and Distributed Systems (TPDS), 2013.
- Wei Shen, Xiang Bai, Rong Hu, Hongyuan Wang, and Longin Jan Latecki. Skeleton Growing and pruning with Bending Potential Ratio. Pattern Recogntion (PR), 2011, 44(2): 196-209. [PDF][Code]
- H. Jiang, W. Liu, D. Wang, C. Tian, X. Bai, X.
Liu, Y. Wu, W. Liu. Connectivity-Based Skeleton Extraction in Wireless Sensor Networks. IEEE Transactions on Parallel and Distributed Systems (TPDS), 2010, 21(5): 710-72.[PDF]
- Y. Tang, X. Bai, et al. Skeletonization with Particle Filters. International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI), 2010, 24(4): 619-634.
- Yao Xu, Bo Wang, Wenyu Liu, and Xiang Bai. Skeleton Graph Matching Based on Critical Points Using Path Similarity [PDF]Asian Conference on Computer Vision (ACCV), Xi'an, China, September 2009.
- Hongbo Jiang, Wenping Liu, Dan Wang, Chen Tian, Xiang Bai, Xue
Liu, Ying Wu, and Wenyu Liu. CASE: Connectivity-based Skeleton Extraction in Wireless Sensor Networks [PDF] Proceedings of IEEE Conference on Computer Communications (INFOCOM),
Rio de Janeiro, Brazil, April 2009.
- Xiang Bai and Longin Jan Latecki. Path Similarity Skeleton Graph Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2008, 30(7):
1282-1292. [PDF](send email for 'OSB' function)
- Quannan Li, Xiang Bai, and Wenyu Liu. Skeletonization of Gray-Scale Images from Incomplete Boundaries [PDF]IEEE International Conference on Image Processing (ICIP), San Diego, California,
USA, October 2008.
- Xiang Bai, Longin Jan Latecki, and WenYu Liu. Skeleton pruning by Contour Partitioning with Discrete Curve Evolution. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2007, 29(3):
449-462. [PDF](code can be found by google)
- Xiang Bai and Longin Jan Latecki. Discrete Skeleton Evolution [PDF]International Conference on Energy Minimization Methods in Computer Vision and Pattern
Recognition (EMMCVPR), Ezhou, Hubei, China, August 2007
- Longin Jan Latecki, Quan-nan Li, Xiang Bai, and Wen-yu Liu. Skeletonization Using SSM of the Distance Transform [PDF]IEEE International Conference on Image Processing (ICIP), San Antonio, Texas, USA,
September 2007
- Xiang Bai, Longin Jan Latecki, and Wenyu Liu. Skeleton pruning by Contour Partitioning [PDF] The 13th International Conference on Discrete Geometry for Computer Imagery (DGCI),
Szeged, Hungary, 2006
Others (Image feature matching, Vehicle recognition, Kinect-based human pose recognition, Face-identification, etc)
- C. Hu, X. Bai, L. Qi, P. Chen, G. Xue, L. Mei. Vehicle Color Recognition with Spatial Pyramid Deep Learning. IEEE Transactions on Intelligent Transportation Systems (TITS), 16(5): 2925-2934,2015.
- C. Hu, X. Bai, L. Qi, X. Wang, G. Xue, L. Mei. Learning Discriminative Pattern for Real-Time Car Brand Recognition. IEEE Transactions on Intelligent Transportation Systems (TITS), 16(6): 3170-3181,2015.
- W. Shen, K. Deng, X. Bai, T. Leyvand, B. Guo, Z. Tu. Exemplar-Based Human Action Pose Correction. IEEE Transactions on Cybernetics (TC), 44(7): 1053-1066, 2014. [PDF]
- Pan Chen, Xiang Bai, Wenyu Liu. Vehicle Color Recognition on Urban Road by Feature Context. IEEE Transactions on Intelligent Transportation Systems (TITS), 15(5): 2340-2346. [PDF] [Dataset]
-
Y. Zhou, Y. Wang, M. Yi, X. Bai, W. Liu, L. J. Latecki. Online Multiple targets Detection and Tracking from Mobile robot in Cluttered indoor Environments with Depth Camera.Int. J. of Pattern Recognition and Aritificial Intelligence (IJPRAI), 2014.
- Jiayi Ma, Ji Zhao, Jinwen Tian, Xiang Bai, Zhuowen Tu. Regularized Vector Field Learning with Sparse Approximation for Mismatch Removal. Pattern Recognition (PR), 2013, 46(12): 3519-3532.
- Wei Shen, Bo Wang, Yueming Wang, Xiang Bai, L.J. Latecki.Face identification using reference-based features with message passing model.Neurocomputing 99: 339-346 (2013)
- Xu Min, Yu Zhou, Shu Liu, Xiang Bai. Real-time Object Tracking via Optimal Feature Subsapce, International Conference on Image Processing (ICIP), 2014.
- W. Shen, K. Deng, X. Bai, T. Leyvand, B. Guo, Z. Tu. Exemplar-Based Human Action Pose Correction and Tagging. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.[PDF]