* indicates the students who are under my supervision/co-supervision.

Car Verification and Recognition

  1. A Large-Scale Car Dataset for Fine-Grained Categorization and Verification
    L. Yang*, P. Luo, C. C. Loy, and X. Tang
    in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
    PDF CompCar Database

Image Segmentation and Parsing

  1. Semantic Image Segmentation via Deep Parsing Network
    Z. Liu*, X. Li*, P. Luo, C. C. Loy, and X. Tang
    in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2015
    PDF Project Page
  2. Clothing Co-Parsing by Joint Image Segmentation and Labeling
    W. Yang*, P. Luo, L. Lin
    in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014
    PDF
  3. Pedestrian Parsing via Deep Decompositional Network
    P. Luo, X. Wang, X. Tang
    in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2013
    PDF Project Page
  4. Hierarchical Face Parsing via Deep Learning
    P. Luo, X. Wang, X. Tang
    Computer Vision and Pattern Recognition (CVPR), 2012
    PDF Press Release
  5. Joint Semantic Segmentation by Searching for Compatible-Competitive References
    P. Luo, X. Wang, L. Lin, X. Tang
    in ACM International Conference on Multimedia (ACM MM), 2012
    PDF

Image Attributes

  1. Deep Learning Face Attributes in the Wild
    Z. Liu*, P. Luo, X. Wang, X. Tang
    IEEE International Conference on Computer Vision (ICCV), 2015
    PDF Project Page CelebA Dataset
  2. A Deep Sum-Product Architecture for Robust Facial Attributes Analysis
    P. Luo, X. Wang, X. Tang
    in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2013
    PDF
  3. Pedestrian Attribute Recognition At Far Distance
    Y. Deng*, P. Luo, C. C. Loy, X. Tang
    ACM Multimedia (ACM MM), short paper, 2014
    Project Page

Object Detection and Recognition

    Face Detection
  1. WIDER FACE: A Face Detection Benchmark
    S. Yang*, P. Luo, C. C. Loy, and X. Tang,
    Technical report, arXiv:1511.06523, 2015
    PDF Project Page
  2. From Facial Parts Responses to Face Detection: A Deep Learning Approach
    S. Yang*, P. Luo, C. C. Loy, and X. Tang,
    in IEEE International Conference on Computer Vision (ICCV), 2015
    PDF Project Page

  3. Pedestrian Detection
  4. Deep Learning Strong Parts for Pedestrian Detection
    Y. Tian*, P. Luo, X. Wang, X. Tang
    in IEEE International Conference on Computer Vision (ICCV), 2015
    PDF
  5. Pedestrian Detection aided by Deep Learning Semantic Tasks
    Y. Tian*, P. Luo, X. Wang, X. Tang
    in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
    PDF Project Page
  6. Switchable deep network for pedestrian detection
    P. Luo, Y. Tian, X. Wang, X. Tang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014
    PDF

  7. Image Recognition
  8. Deep Representation Learning with Target Coding
    S. Yang*, P. Luo, C. C. Loy, K. W. Shum, X. Tang,
    in the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), Oral (nominated as easily accessable paper), 2015
    PDF Project Page

  9. Object Detection
  10. Learning Compositional Shape Models of Multiple Distance Metrics by Information Projection
    P. Luo, L. Lin, X. Liu
    in IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2015
    PDF
  11. DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
    W. Ouyang, X. Wang, X. Zeng, S. Qiu, P. Luo, Y. Tian, H. Li, S. Yang, Z. Wang, C. Loy, X. Tang
    in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
    PDF
  12. DeepID-Net: Multi-stage and Deformable Deep Convolutional Neural Networks for Object Detection
    W. Ouyang, P. Luo, X. Zeng, S. Qiu, Y. Tian, H. Li, S. Yang, Z. Wang, Y. Xiong, C. Qian, Z. Zhu, R. Wang, C. C. Loy, X. Wang, X. Tang
    Technical Report, arXiv:1409.3505, 2014
    PDF Project Page
  13. Representing and recognizing objects with massive local image patches
    L Lin, P. Luo, X Chen, K Zeng
    Pattern Recognition 45 (1), 231-240 (PR), 2012
    PDF
  14. Learning shape detector by quantizing curve segments with multiple distance metrics
    P. Luo, L Lin, H Chao
    in Proceedings of European Conference on Computer Vision (ECCV), 2010
    PDF
  15. A Discriminative Model for Object Representation and Detection via Sparse Features
    X. Song, P. Luo, L. Lin, Y. Jia
    International Conference on Pattern Recognition (ICPR), 2010

Face Verification and Recognition

  1. Face Model Compression by Distilling Knowledge from Neurons
    P. Luo, Z. Zhu, Z. Liu, X. Wang, and X. Tang
    in the 30th AAAI Conference on Artificial Intelligence (AAAI), 2016
  2. Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations
    Z. Zhu*, P. Luo, X. Wang, X. Tang
    Advances in Neural Information Processing Systems (NIPS), 2014
  3. Recover Canonical-View Faces in the Wild with Deep Neural Networks
    Z. Zhu*, P. Luo, X. Wang, X. Tang
    Technical report, arXiv:1404.3543, 2014
    PDF
  4. Deep Learning Identity-preserving Face Space
    Z. Zhu*, P. Luo, X. Wang, X. Tang
    in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2013
    PDF Project Page
  5. Deep learning multi-view representation for face recognition
    Z. Zhu*, P. Luo, X. Wang, X. Tang
    Technical report, arXiv:1406.6947, 2014
    PDF

Face Relation Traits Analysis

  1. Learning Social Relation Traits from Face Images
    Z. Zhang*, P. Luo, C. C. Loy, X. Tang
    in IEEE International Conference on Computer Vision (ICCV), 2015
    PDF Project Page

Face Alignment

  1. Learning Deep Representation for Face Alignment with Auxiliary Attributes
    Z. Zhang*, P. Luo, C. C. Loy, X. Tang
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015
    PDF Project Page
  2. Facial Landmark Detection by Deep Multi-task Learning
    Z. Zhang*, P. Luo, C. C. Loy, X. Tang
    in Proceedings of European Conference on Computer Vision (ECCV), 2014
    PDF Project Page
  3. Learning and Transferring Multi-task Deep Representation for Face Alignment
    Z. Zhang*, P. Luo, C. C. Loy, X. Tang
    Technical report, arXiv:1408.3967, 2014
    PDF Project Page

2D Cartoon Stylization, 3D Perception

  1. Semantics-driven portrait cartoon stylization
    M. Yang, S. Lin, P. Luo, L. Lin, H. Chao
    IEEE International Conference on Image Processing (ICIP), 2010
    PDF
  2. Hierarchical 3D perception from a single image
    P. Luo, J. He, L. Lin, H. Chao
    IEEE International Conference on Image Processing (ICIP), 2009
    PDF

2017

  1. Deep Dual Learning for Semantic Image Segmentation
    P. Luo†, G. Wang†, L. Lin, X. Wang
    International Conference on Computer Vision (ICCV), 2017, to appear († co-first authors)
    A novel learning setting called Deep Dual Learning for image segmentation is presented and achieved recent state-of-the-art accuracy of 86.8% on the Pascal VOC 2012 segmentation test set.

  2. Unconstrained Fashion Landmark Detection via Hierarchical Recurrent Transformer Networks
    S. Yan, Z. Liu, P. Luo, S. Qiu, X. Wang, and X. Tang
    ACM Multimedia (MM), 2017, (Full Research Paper)
    The joint laboratory of CUHK Multimedia Lab and SenseTime Research has devoted large efforts to understand fashion images. For more solutions and details, please visit DeepFashion and contact Shi Qiu and me.

  3. Deep Learning Markov Random Field for Semantic Segmentation
    Z. Liu, X. Li, P. Luo, C. C. Loy, X. Tang
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017

  4. Video Object Segmentation with Re-identification
    X. Li, Y. Qi, Z. Wang, K. Chen, Z. Liu, J. Shi, P. Luo, C. Change Loy, X. Tang
    The 2017 DAVIS Challenge on Video Object Segmentation - CVPR Workshops, 2017
    First entry of the 2017 DAVIS Challenge on Video Object Segmentation.

  5. Learning Deep Architectures via Generalized Whitened Neural Networks
    P. Luo
    The Thirty-fourth International Conference on Machine Learning (ICML), 2017, to appear

  6. EigenNet: Towards Fast and Structural Learning of Deep Neural Networks
    P. Luo
    International Joint Conference on Artificial Intelligence (IJCAI), 2017, to appear

  7. Learning Object Interactions and Descriptions for Semantic Image Segmentation
    P. Luo†, G. Wang*†, L. Lin, X. Wang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 († co-first authors)
    We achieved a recent state-of-the-art of 86.3% accuracy on Pascal VOC 2012 segmentation test set.

  8. Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade
    X. Li*, Z. Liu*, P. Luo, C.C. Loy, X. Tang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (Spotlight)

  9. Deep Learning Face Attributes for Detection and Alignment
    C.C. Loy, P. Luo, C. Huang
    in Book Visual Attributes, 2017

  10. Faceness-Net: Face Detection through Deep Facial Part Responses
    S. Yang*, P. Luo, C.C. Loy, X. Tang
    arXiv:1701.08393, 2017

  11. DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks
    W. Ouyang, X. Zeng, X. Wang, S. Qiu, P. Luo et al.
    IEEE Transactions on Pattern Analysis & Machine Intelligence (TPAMI), 2017, Issue No. 07 - July (vol. 39)

2016

  1. Deep Learning Markov Random Field for Semantic Segmentation
    Z. Liu*, X. Li*, P. Luo, C.C. Loy, X. Tang
    arXiv:1606.07230, 2016
    DPN was extended to video segmentation.

  2. From Facial Expression Recognition to Interpersonal Relation Prediction
    Z. Zhang*, P. Luo, C.C. Loy, X. Tang
    arXiv:1609.06426, 2016
    A large-scale facial expression dataset of over 90K images will be released.

  3. Joint face representation adaptation and clustering in videos
    Z. Zhang*, P. Luo, C.C. Loy, X. Tang
    European Conference on Computer Vision (ECCV), 2016

  4. Fashion Landmark Detection in the Wild
    Z. Liu*, S. Yan*, P. Luo, X. Wang, X. Tang
    European Conference on Computer Vision (ECCV), 2016

  5. Wider face: A face detection benchmark
    S. Yang*, P. Luo, C.C. Loy, X. Tang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Oral)

  6. Deepfashion: Powering robust clothes recognition and retrieval with rich annotations
    Z. Liu*, P. Luo, S. Qiu, X. Wang, X. Tang,
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016

  7. Face Model Compression by Distilling Knowledge from Neurons
    P. Luo†, Z. Zhu†, Z. Liu, X. Wang, X. Tang,
    in the 30th AAAI Conference on Artificial Intelligence (AAAI), 2016 (Oral)
    († indicates co-first authors who contributed equally.)
    Neuron selection is proposed to select informative neurons for deep model compression. These neurons are selected by using domain knowledge of the learned face representation.

  8. Clothes Co-Parsing via Joint Image Segmentation and Labeling with Application to Clothing Retrieval
    X. Liang, L. Lin, W. Yang, P. Luo, J. Huang, S. Yan
    IEEE Transactions on Multimedia (TMM) (Volume: 18, Issue: 6), 2016

2015

  1. WIDER FACE: A Face Detection Benchmark
    S. Yang*, P. Luo, C. C. Loy, X. Tang,
    Technical Report, arXiv:1511.06523, 2015
    We have proposed a new face detection benchmark, which is 10 times larger than the existing datasets.

  2. Semantic Image Segmentation via Deep Parsing Network
    Z. Liu*, X. Li*, P. Luo, C. C. Loy, X. Tang,
    IEEE International Conference on Computer Vision (ICCV), 2015 (Oral)
    We disclosed the close connections between CNN and the mean field (MF) inference of CRF. Several convolution layers are carefully designed to approximate MF, making one step of MF achieve remarkable accuracy of 77.5% on the Pascal VOC 2012 segmentation dataset.

  3. Deep Learning Strong Parts for Pedestrian Detection
    Y. Tian*, P. Luo, X. Wang, X. Tang,
    IEEE International Conference on Computer Vision (ICCV), 2015
    We achieved 11.89% miss rate on the Caltech pedestrian dataset.
  4. Deep Learning Face Attributes in the Wild
    Z. Liu*, P. Luo, X. Wang, X. Tang,
    IEEE International Conference on Computer Vision (ICCV), 2015
    Several valuable facts are disclosed for deep learning face representation.
  5. From Facial Parts Responses to Face Detection: A Deep Learning Approach
    S. Yang*, P. Luo, C. C. Loy, X. Tang,
    IEEE International Conference on Computer Vision (ICCV), 2015
    Face attributes help localize face parts. We achieved state-of-the-art face detection performance on FDDB, AFW, and Pascal Face datasets.
  6. Learning Social Relation Traits from Face Images
    Z. Zhang*, P. Luo, C. C. Loy, X. Tang,
    IEEE International Conference on Computer Vision (ICCV), 2015
    The first attempt to learn social traits from a pair of face images using deep networks.
  7. Pedestrian Detection aided by Deep Learning Semantic Tasks
    Y. Tian*, P. Luo, X. Wang, X. Tang,
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
    Achieved state-of-the-art results on Caltech and ETH pedestrian detection benchmark
  8. A Large-Scale Car Dataset for Fine-Grained Categorization and Verification
    L. Yang*, P. Luo, C. C. Loy, X. Tang,
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
    A large-scale dataset for vechicle analysis with 136,726 images

  9. DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
    W. Ouyang, X. Wang, X. Zeng, S. Qiu, P. Luo, Y. Tian, H. Li, S. Yang, Z. Wang, C. Loy, X. Tang,
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
    state-of-the-art result on ImageNet object detection challenge
  10. Deep Representation Learning with Target Coding
    S. Yang*, P. Luo, C. C. Loy, K. W. Shum, X. Tang,
    in the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), Oral, 2015
    nominated as easily accessable paper, 8/531=1.5%; invited talk in IEEE Conference on Robotics and Automation (ICRA), 2015
  11. Learning Compositional Shape Models of Multiple Distance Metrics by Information Projection
    P. Luo, L. Lin, X. Liu,
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2015
  12. Learning Deep Representation for Face Alignment with Auxiliary Attributes
    Z. Zhang*, P. Luo, C. C. Loy, X. Tang
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015
    Best performance so far of the 300-W face landmark detection challenge. See how to formulate multi-task CNN within a unified probabilistic framework, including adaptive learning rates of tasks and correlations between tasks.

2014

  1. Pedestrian Detection aided by Deep Learning Semantic Tasks
    Y. Tian*, P. Luo, X. Wang, X. Tang
    Technical Report, arXiv:1412.0069, 2014
  2. Deep Learning Face Attributes in the Wild
    Z. Liu*, P. Luo, X. Wang, X. Tang
    Technical Report, arXiv:1411.7766, 2014
    disclosing strong connections between deeply learned face representations and face attributes
  3. Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations
    Z. Zhu*, P. Luo, X. Wang, X. Tang
    Advances in Neural Information Processing Systems (NIPS), 2014
    a new model to disentange hidden factors (identities, views, expressions, and illuminations, etc) for face recognition
  4. DeepID-Net: Multi-stage and Deformable Deep Convolutional Neural Networks for Object Detection
    W. Ouyang, P. Luo, X. Zeng, S. Qiu, Y. Tian, H. Li, S. Yang, Z. Wang, Y. Xiong, C. Qian, Z. Zhu, R. Wang, C. C. Loy, X. Wang, X. Tang
    Technical Report, arXiv:1409.3505, 2014
  5. Facial Landmark Detection by Deep Multi-task Learning
    Z. Zhang*, P. Luo, C. C. Loy, X. Tang
    in Proceedings of European Conference on Computer Vision (ECCV), 2014
  6. Learning and Transferring Multi-task Deep Representation for Face Alignment
    Z. Zhang*, P. Luo, C. C. Loy, X. Tang
    Technical report, arXiv:1408.3967, 2014
  7. Recover canonical-view faces in the wild with deep neural networks
    Z. Zhu*, P. Luo, X. Wang, X. Tang
    Technical report, arXiv:1404.3543, 2014
    learning to reconstruct 2D frontal faces in the wild via CNNs
  8. Deep learning multi-view representation for face recognition
    Z. Zhu*, P. Luo, X. Wang, X. Tang
    Technical report, arXiv:1406.6947, 2014
  9. Switchable deep network for pedestrian detection
    P. Luo, Y. Tian, X. Wang, X. Tang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014

  10. Clothing Co-Parsing by Joint Image Segmentation and Labeling
    W. Yang*, P. Luo, L. Lin
    in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014
  11. Pedestrian Attribute Recognition At Far Distance
    Y. Deng*, P. Luo, C. C. Loy, X. Tang
    ACM Multimedia (ACM MM), short paper, 2014
    A large dataset for pedestrian attribute recognition.

2013

  1. A Deep Sum-Product Architecture for Robust Facial Attributes Analysis
    P. Luo, X. Wang, X. Tang
    in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2013
  2. Pedestrian parsing via deep decompositional network
    P. Luo, X. Wang, X. Tang
    in Proceedings of IEEE International Conference on Computer Vision(ICCV), 2013

  3. Deep learning identity-preserving face space
    Z. Zhu*, P. Luo, X. Wang, X. Tang
    in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2013

2012

  1. Hierarchical face parsing via deep learning
    P. Luo, X. Wang, X. Tang
    Computer Vision and Pattern Recognition (CVPR), 2012
    the first work applying RBM to face analysis and image parsing
  2. Joint semantic segmentation by searching for compatible-competitive references
    P. Luo, X. Wang, L. Lin, X. Tang
    in ACM International Conference on Multimedia (ACM MM), 2012
  3. Representing and recognizing objects with massive local image patches
    L Lin, P. Luo, X Chen, K Zeng
    Pattern Recognition 45 (1), 231-240 (PR), 2012

Before 2012

  1. Learning shape detector by quantizing curve segments with multiple distance metrics
    P. Luo, L Lin, H Chao
    in Proceedings of European Conference on Computer Vision (ECCV), 2010
  2. A Discriminative Model for Object Representation and Detection via Sparse Features
    X. Song, P. Luo, L. Lin, Y. Jia
    International Conference on Pattern Recognition (ICPR), 2010
  3. Semantics-driven portrait cartoon stylization
    M. Yang, S. Lin, P. Luo, L. Lin, H. Chao
    IEEE International Conference on Image Processing (ICIP), 2010
  4. Hierarchical 3D perception from a single image
    P. Luo, J. He, L. Lin, H. Chao
    IEEE International Conference on Image Processing (ICIP), 2009