List of Publications

Please also see my Google Scholar page for the full list of publications.

Conference and Journal

2017

  • Deep Free-Form Deformation Network for Object-Mask Registration, [pdf]
    Haoyang Zhang, Xuming He
    International Conference on Computer Vision (ICCV), 2017

  • Efficient Scene Layout Aware Object Detection for Traffic Surveillance, [pdf]
    Tao Wang, Xuming He, Songzhi Su, Yin Guan
    IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017.
    Traffic Surveillance Workshop and Challenge Best Paper Award.

  • Forest Change Detection in Incomplete Satellite Images With Deep Neural Networks, [link]
    Salman H. Khan, Xuming He, Fatih Porikli, Mohammed Bennamoun
    IEEE Transactions on Geoscience and Remote Sensing, 2017.

  • Learning deep structured network for weakly supervised change detection, [pdf]
    Salman Khan, Xuming He, Fatih Porikli, Ferdous Sohel, Roberto Togneri, Mohammed Bennamoun International Joint Conference on Artificial Intelligence (IJCAI), 2017

  • Boundary-aware Instance Segmentation, [pdf]
    Zeeshan Hayder, Xuming He, Mathieu Salzmann
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

  • Indoor Scene Parsing with Instance Segmentation, Semantic Labeling and Support Relationship Inference, [pdf]
    Wei Zhuo, Mathieu Salzmann, Xuming He, Miaomiao Liu
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

  • Predicting Salient Face in Multiple-face Videos, [pdf]
    Yufan Liu, Songyang Zhang, Mai Xu, Xuming He
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

  • Stacked Learning to Search for Scene Labeling, [link]
    Feiyang Cheng, Xuming He, Hong Zhang
    IEEE Transactions on Image Processing, 2017

  • Learning Spatial Transforms for Refining Object Segment Proposals, [pdf]
    Haoyang Zhang, Xuming He, Fatih Porikli
    IEEE Winter Conference on Applications of Computer Vision (WACV), 2017

2016

  • Learning to Generate Object Proposals with Multi-modal Cues, [pdf]
    Haoyang Zhang, Xuming He, Fatih Porikli
    Asian Conference on Computer Vision (ACCV), 2016

  • Object-Aware Dictionary Learning with Deep Features, [pdf]
    Yurui Xie, Fatih Porikli, Xuming He
    Asian Conference on Computer Vision (ACCV), 2016

  • Learning Dynamic Hierarchical Models for Anytime Scene Labeling, [pdf] [arXiv]
    Buyu Liu, Xuming He
    European Conference on Computer Vision (ECCV), 2016

  • Building Scene Models by Completing and Hallucinating Depth and Semantics, [pdf]
    Miaomiao Liu, Xuming He, Mathieu Salzmann
    European Conference on Computer Vision (ECCV), 2016

  • Semantic Context and Depth-aware Object Proposal Generation, [pdf]
    Haoyang Zhang, Xuming He, Fatih Porikli, Laurent Kneip
    IEEE International Conference on Image Processing (ICIP), 2016

  • Learning to Co-Generate Object Proposals with a Deep Structured Network, [pdf]
    Zeeshan Hayder, Xuming He, Mathieu Salzmann
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016

  • SentiCap: Generating Image Descriptions with Sentiments, [pdf] [arXiv]
    Alexander Mathews, Lexing Xie, Xuming He
    AAAI Conference on Artificial Intelligence (AAAI-16), 2016

  • Contour Completion without Region Segmentation, [link] [pdf]
    Yansheng Ming, Hongdong Li, Xuming He
    IEEE Transactions on Image Processing, vol. 25, no. 8, pp 3597–3611, 2016

2015

  • Structural Kernel Learning for Large Scale Multiclass Object Co-Detection, [pdf]
    Zeeshan Hayder, Xuming He, Mathieu Salzmann
    International Conference on Computer Vision (ICCV), 2015

  • Studying Object Naming with Online Photos and Caption, [pdf]
    Alexander Mathews, Lexing Xie, Xuming He
    Multimedia COMMONS, A Workshop at ACM Multimedia, 2015

  • Multiclass Semantic Video Segmentation with Object-Level Active Inference, [pdf] [suppl zip]
    Buyu Liu, Xuming He
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015

  • Indoor Scene Structure Analysis for Single Image Depth Estimation, [pdf]
    Wei Zhuo, Mathieu Salzmann, Xuming He, Miaomiao Liu
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015

  • Separating Objects and Clutter in Indoor Scenes, [pdf] [suppl pdf]
    Salman H. Khan, Xuming He, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015

  • Choosing Basic-Level Concept Names using Visual and Language Context, [pdf] [suppl pdf]
    Alexander Mathews, Lexing Xie, Xuming He
    IEEE Winter Conference on Applications of Computer Vision (WACV), 2015

  • Multiclass Semantic Video Segmentation with Exemplar-based Object Reasoning, [pdf]
    Buyu Liu, Xuming He, Stephen Gould
    IEEE Winter Conference on Applications of Computer Vision (WACV), 2015

  • Motion Segmentation of Truncated Signed Distance Function Based Volumetric Surfaces, [pdf]
    Samunda Perera, Nick Barnes, Xuming He, Shahram Izadi, Pushmeet Kohli, Ben Glocker
    IEEE Winter Conference on Applications of Computer Vision (WACV), 2015

  • Robust Face Alignment Under Occlusion via Regional Predictive Power Estimation, [link] [pdf]
    Heng Yang, Xuming He, Xuhui Jia, I. Patras
    IEEE Transactions on Image Processing, vol.24, no.8, pp 2393–2403, 2015

2014

  • Object Co-Detection via Efficient Inference in a Fully-Connected CRF, [pdf]
    Zeeshan Hayder, Mathieu Salzmann, Xuming He
    European Conference on Computer Vision (ECCV), 2014

  • Superpixel Graph Label Transfer with Learned Distance Metric, [pdf]
    Stephen Gould, Jiecheng Zhao, Xuming He, Yuhang Zhang
    European Conference on Computer Vision (ECCV), 2014

  • An Exemplar-based CRF for Multi-instance Object Segmentation, [pdf]
    Xuming He, Stephen Gould
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014

  • Discrete-Continuous Depth Estimation from a Single Image, [pdf]
    Miaomiao Liu, Mathieu Salzmann, Xuming He
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014

  • Joint Semantic and Geometric Segmentation of Videos with a Stage Model, [pdf]
    Buyu Liu, Xuming He, Stephen Gould
    IEEE Winter Conference on Applications of Computer Vision (WACV), 2014

  • Data-Driven Street Scene Layout Estimation for Distant Object Detection, [pdf]
    Donghao Zhang, Xuming He, Hanxi Li
    International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2014

  • The Effectiveness of Prosthetic Fixation for Recognizing Faces in Natural Scenes, [poster pdf]
    Janine Walker, Xuming He, Hanxi Li and Nick Barnes
    Annual Meeting of the Association for Research in Vision and Ophthalmology (ARVO), 2014

  • Winding Number Constrained Contour Detection, [link] [pdf]
    Yansheng Ming, Hongdong Li, Xuming He
    IEEE Transactions on Image Processing, vol. 24, no. 1, pp 68–79, 2014

  • Scene Understanding by Labeling Pixels, [link] [pdf]
    Stephen Gould, Xuming He
    Communications of the ACM, vol. 57, no. 11, pp 68–77, 2014

  • A New Theoretical Approach to Improving Face Recognition in Disorders of Central Vision: Face caricaturing, [link] [pdf]
    Jessica Irons, Elinor McKone, Rachael Dumbleton, Nick Barnes, Xuming He, Jan Provis, Callin Ivanovici, Alisa Kwa
    Journal of Vision, 14(2):12. 2014.

2013

  • Learning Structured Hough Voting for Joint Object Detection and Occlusion Reasoning, [pdf]
    Tao Wang, Xuming He, Nick Barnes
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013

  • Winding Number for Region-Boundary Consistent Salient Contour Extraction, [pdf]
    Yansheng Ming, Hongdong Li, Xuming He
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013

  • Picture Tags and World Knowledge: Learning Tag Relations from Visual Semantic Sources, [pdf]
    Lexing Xie, Xuming He
    The 21st ACM International Conference on Multimedia (ACM MM), 2013

  • Symmetry Detection via Contour Grouping, [pdf]
    Yansheng Ming, Hongdong Li, Xuming He
    IEEE International Conference on Image Processing (ICIP), 2013

  • Glass Object Segmentation by Label Transfer on Joint Depth and Apearance Manifolds, [pdf]
    Tao Wang, Xuming He, Nick Barnes
    IEEE International Conference on Image Processing (ICIP), 2013

  • Tracking Large-scale Video Remix in Real-world Events, [link] [pdf]
    Lexing Xie, Apostol Natsev, Xuming He, John Kender, Matthew Hill, John R Smith
    IEEE Transactions on Multimedia, 15(6), 2013.

2012

  • Connected Contours: a Contour Completion Model That Respects Closure-Effect, [pdf]
    Yansheng Ming, Hongdong Li, Xuming He
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012

  • Glass Object Localization by Joint Inference of Boundary and Depth, [pdf]
    Tao Wang, Xuming He, Nick Barnes
    International Conference on Pattern Recognition (ICPR), 2012

  • The Role of Vision Processing in Prosthetic Vision,
    Nick Barnes, Xuming He, Chris McCarthy, Lachlan Horne, Junae Kim, Adele Scott and Paulette Lieby
    Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), 2012

  • An Face-based Visual Fixation System for Prosthetic Vision,
    Xuming He, Junae Kim, Nick Barnes
    Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), 2012

  • Probabilistic Models of Vision and Max-margin Methods, [link] [pdf]
    Alan Yuille and Xuming He
    Frontiers of Electrical and Electronic Engineering, 7(1), 94-106, 2012.

2011

  • Laplacian Margin Distribution Boosting for Learning from Sparsely Labeled Data, [pdf]
    Tao Wang, Xuming He, Chunhua Shen, Nick Barnes
    International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2011

  • Face Detection and Tracking in Video To Facilitate Face Recognition in a Visual Prothesis, [poster pdf]
    Xuming He, Chunhua Shen, Nick Barnes
    Annual Meeting of the Association for Research in Vision and Ophthalmology (ARVO), 2011

2010

  • A Unified Model of Short-range and Long-range Motion Perception, [pdf]
    Shuang Wu, Xuming He, Hongjing Lu, and Alan Yuille
    Annual Conference on Neural Information Processing Systems (NIPS), 2010

  • Occlusion Boundary Detection using Pseudo-Depth, [pdf]
    Xuming He and Alan Yuille
    European Conference on Computer Vision (ECCV), 2010

2008

  • Learning Hybrid Models for Image Annotation with Partially Labeled Data, [pdf]
    Xuming He, and Richard S. Zemel
    Annual Conference on Neural Information Processing Systems (NIPS), 2008

  • Latent Topic Random Fields: Learning Using a Taxonomy of Labels, [pdf (with Appendix)]
    Xuming He, and Richard S. Zemel
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008

  • Learning Flexible Features for Conditional Random Fields, [link] [pdf]
    Liam Stewart, Xuming He, Richard S. Zemel
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(8), 1415-1426, 2008.

2007  — 

  • Topological Map Learning from Outdoor Image Sequences, [link] [pdf]
    Xuming He, Richard Zemel, and Volodymyr Mnih
    Journal of Field Robotics, 23, 1091-1104, 2007.

  • Learning and Incorporating Top-down Cues in Image Segmentation, [pdf]
    Xuming He, Richard Zemel, and Deb Ray
    European Conference on Computer Vision (ECCV), 2006.

  • Learning Landmarks for Localization via Manifolds,
    Xuming He, Richard Zemel, and Volodymyr Mnih
    NIPS Workshop on Machine Learning Based Robotics in Unstructured Environments, 2005

  • Multiscale Conditional Random Fields for Image Labelling, [pdf]
    Xuming He, Richard Zemel, and Miguel Carreira-Perpinan
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2004

Ph.D. Thesis

  • Xuming He, Learning Structured Prediction Models for Image Labeling, PhD thesis, Department of Computer Science, University of Toronto, 2008 [pdf]

Technical Reports

  • Weakly Supervised Change Detection in a Pair of Images, [arXiv]
    Salman H Khan, Xuming He, Mohammed Bennamoun, Fatih Porikli, Ferdous Sohel, Roberto Togneri
    Arxiv, 2016

  • Semantic-Aware Depth Super-Resolution in Outdoor Scenes, [arXiv]
    Miaomiao Liu, Mathieu Salzmann, Xuming He
    Arxiv, 2016

  • Structured Depth Prediction in Challenging Monocular Video Sequences, [arXiv]
    Miaomiao Liu, Mathieu Salzmann, Xuming He
    Arxiv, 2015