On person parsing


Liang-Chieh Chen: http://liangchiehchen.com/
Yi Yang: http://www.ics.uci.edu/~yyang8/
Xiaodan Liang: http://www.cs.cmu.edu/~xiaodan1/
Liang lin: http://hcp.sysu.edu.cn/home/
Shuicheng Yan:
Alan L. Yuille:



  • 2017 CVPR Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing
  • 2016 CVPR Deep Structured Scene Parsing by Learning with Image Descriptions
  • 2016 CVPR Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
  • 2016 CVPR Attention to Scale: Scale-aware Semantic Image Segmentation
  • 2015 CVPR Matching-CNN Meets KNN: Quasi Parametric Human Parsing
    • S. Liu, X. Liang, L. Liu, X. Shen, J. Yang, C. Xu, L. Lin, X. Cao, and S. Yan
  • 2015 CVPR Fully convolutional networks for semantic segmentation
    • J. Long, E. Shelhamer, and T. Darrell
  • 2012 CVPR Parsing clothing in fashion photographs
    • K. Yamaguchi, M. Kiapour, L. Ortiz, and T. Berg


  • 2015 ICCV Human parsing with contextualized convolutional neural network
    • X. Liang, C. Xu, X. Shen, J. Yang, S. Liu, J. Tang, L. Lin, and S. Yan
  • 2015 ICCV Joint object and part segmentation using deep learned potentials
    • P. Wang, X. Shen, Z. Lin, S. Cohen, B. Price, and A. Yuille.
  • 2013 ICCV Retrieving similar styles to parse clothing items
    • K. Yamaguchi, M. Kiapour, and T. Berg
  • 2015 ICCV Weakly- and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation


  • 2016 ECCV Zoom better to see clearer: Huamn part segmentation with auto zoom net
    • F. Xia, P. Wang, L.-C. Chen, and A. L. Yuille
  • 2016 ECCV LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling


  • 2017 PAMI DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs(DeepLab2)
  • 2015 ICLR Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
  • 2016 AAAI Pose-guided human parsing by an and/or graph using pose-context features
    • F. Xia, J. Zhu, P. Wang, and A. Yuille
  • 2016 PAMI Human Parsing with Contextualized Convolutional Neural Network
  • 2015 ArXiv Segnet: A deep convolutional encoder-decoder architecture for image segmentation
    • V. Badrinarayanan, A. Kendall, and R. Cipolla
  • 2015 PAMI Deep human parsing with active template regression
    • X. Liang, S. Liu, X. Shen, J. Yang, L. Liu, J. Dong, L. Lin,and S. Yan
  • 2014 ACCV A High Performance CRF Model for Clothes Parsing
    • E. Simo-Serra, S. Fidler, F. Moreno-Noguer, and R. Urtasun


  • Microsoft Coco(COCO)
  • Look into person(LIP)
    • http://hcp.sysu.edu.cn/lip/index.php
    • contains 50,000 images with elaborated pixel-wise annotations with 19 semantic human part labels and 2D human poses with 16 key points.
    • The metrics are reported by FCN. The four metrics are Pixel accuracy(%) , Mean accuracy(%), Mean IoU(%) and Frequency weighted IoU(%).
    • The images in the LIP dataset are cropped person instances from Microsoft COCO [19] training and validation sets. there are 50,462 images in the LIP dataset including 19,081 full-body images, 13,672 upper-body images, 403 lower-body images, 3,386 head-missed images, 2,778 back-view images and 21,028 images with occlusions
  • ATR
    • X. Liang, C. Xu, X. Shen, J. Yang, S. Liu, J. Tang, L. Lin, and S. Yan. Human parsing with contextualized convolutional neural network. In ICCV, 2015
    • 16000 training image, 700 validation images, 1000 testing image, with 18 cateogries.
  • PASCAL-Person-Part:
    • X. Chen, R. Mottaghi, X. Liu, S. Fidler, R. Urtasun, et al.Detect what you can: Detecting and representing objects using holistic models and body parts. In CVPR, 2014.
    • 1716 training image, 1817 testing images, and 7 categories.
  • Fashionista
    • K. Yamaguchi, M. Kiapour, L. Ortiz, and T. Berg. Parsing clothing in fashion photographs. In CVPR, 2012
    • 456 training image, 229 testing image, with 56 categories
  • Kinect2 Human Pose Dataset (K2HPD)