Code & Data

注意事项: These resources might need password to be opened. Please supply your name, institute and positions to get the password. Click HERE to do this. These source code are free for research and education use only. Please cite our paper if you use any part of our source code or data in your research.

Source code

  1. Source code: FLIC: Fast Linear Iterative Clustering with Active Search, AAAI, 2018. [project] [bib]
  2. C++: GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence, IEEE CVPR, 2017. [project][bib]
  3. Source code: Deeply supervised salient object detection with short connections, IEEE CVPR, 2017. [project] [bib]
  4. Source code: Richer Convolutional Features for Edge Detection, IEEE CVPR, 2017. [project] [bib]
  5. Source Code: Structure-measure: A New Way to Evaluate Foreground Maps, IEEE ICCV, 2017. [project] [bib]
  6. C++:  Salient Object Detection: A Discriminative Regional Feature Integration Approach, IJCV, 2017. [project] [bib]
  7. C++: HFS: Hierarchical Feature Selection for Efficient Image Segmentation. ECCV, 2016. [project][bib]
  8. C++ & Matlab: Salient Object Detection: A Benchmark, IEEE TIP, 2015. [project]
  9. C++ & CUDA: Struck: Structured output tracking with kernels, IEEE TPAMI, 2016. [pdf]
  10. C++ & CUDA: SemanticPaint: Interactive 3D Labeling and Learning at your Fingertips, ACM TOG 2015. [project]
  11. C++: DenseCut: Densely Connected CRFs for Realtime GrabCut, CGF 2015. [project] (I didn’t get enough time to reorganize the code. This is an initial version code without careful comments and organization.)
  12. C++ & CUDA: A Framework for the Volumetric Integration of Depth Images, arxiv eprint, 2014. [project]
  13. C++: ‘BING: Binarized Normed Gradients for Objectness Estimation at 300fps’, IEEE CVPR 2014. [project] [bib][readme]
  14. C++: Efficient Salient Region Detection with Soft Image Abstraction”, IEEE ICCV 2013. [project] [bib]
  15. C++(speech recognition part): “ImageSpirit: Verbal Guided Image Parsing”, ACM TOG, 2014, [bib] [project]。 Full code from Github.
  16. C++: “Global Contrast based Salient Region Detection”, IEEE TPAMI 2015. [project] [FAQs] [bib]
  17. C++: “Curve Structure Extraction for Cartoon Images” [Pdf] [bib]
  18. Executable 和 C++: “A Shape-Preserving Approach to Image Resizing”. CGF 2009. [project] [bib]
  19. Commercial version (神笔小Q, powered by QQ实验室) for our paper “Sketch2Photo: Internet Image Montage“, ACM TOG, 2009. [bib]
  20. Matlab: “Connectedness of Random Walk Segmentation”, IEEE TPAMI 2009. [bib]


  • aNYU: attributes augmented NYU dataset published with our CVPR 2014 paper “Dense Semantic Image Segmentation with Objects and Attributes” (Please follow the instructions in the project page for getting unzip password).
  • THUR15K (787MB): Salient object region labeling (annotated at pixel accuracy if exist such an salient object) for 15000 non-selected internet images, divided into five groups according to the keywords used to download them. Please cite our paper [BIB] if you use it. We also provide matlab file of Fig. 7(b) for easier comparison.
  • MSRA10K: Pixel accurate salient object labeling for 10000 images from MSRA dataset.
  • PASCAL VOC annotations: Unfortunately, the xml format used in one of the most widely used benchmark dataset (PASCAL VOC) does not compatible with OpenCV. Here is an yml version of PASCAL VOC annotations (VOC 2007), which could be read by OpenCV directly.


International patents:

  1. Image processing method and image processing device, Shi-Min Hu, Ming-Ming Cheng, Guo-Xin Zhang, Niloy J. Mitra, Xiang Ruan, US20120288189, EP2523165, CN102779338A, JP2012243313A
  2. Method for calculating image visual saliency based on color histogram and overall contrast, Shi-Min Hu, Ming-Ming Cheng, Guo-Xin Zhang, WO 2012122682, PCT/CN2011/000690
  3. Method for detecting similar units based on outline belt graph, Shi-Min Hu, Ming-Ming Cheng, Fang-Lue Zhang, WO 2011131029, CN 101833668

Chinese patents (SooPat):

  1. 侯淇彬,程明明,白蔚,周迅溢,图像显著性物体检测方法和装置,申请号:201710488970.4,申请日:2017年6月26日。
  2. 程明明,刘笑畅,白蔚,苗磊,一种图片处理方法及设备,申请号:201710602208.4,申请日期:2017年7月24日。
  3. 程明明,刘云,侯淇彬,白蔚,图像分割方法及装置,申请号:201610850223.6,申请日:2016年9月28日。
  4. 胡事民,张方略,程明明,基于成组物体混合的图像合成方法,申请号:201110262737.7 申请日:2011-09-06。
  5. 胡事民,程明明,张国鑫,基于色彩直方图和全局对比度的图像视觉显著性计算方法,申请号:201110062520.1, 授权日:2012年7月25日。
  6. 胡事民,程明明,张方略,一种基于轮廓带图的相似单元检测方法,申请号:201010159931.8, 授权日: 2011年12月28日。
  7. 胡事民,程明明,张方略,基于几何信息的相似图元隐藏部分自动补全方法,申请号:201010158440.1,授权日: 2012年9月5日。
  8. 胡事民,程明明,张国鑫,一种基于共形能量的内容敏感图像缩放方法,申请号:200910092756.2,授权日2011年12月28日。
  9. 胡事民,陈韬,程明明,张松海,基于图像库的图像合成质量自动评测方法,申请号:200910086937.4,受权日2011年9月14日。
  10. 胡事民,陈韬,程明明,张松海,基于混合梯度场和混合边界条件的图像合成方法和装置,申请号:200910084769.5,授权日2011年5月11日。
  11. 胡事民,程明明,陈韬,张松海,一种基于草图的网络图元自动提取方法和系统,申请号:200910081069,授权日2010年9月1日。
  12. 胡事民,张一飞,程明明,视频像素可伸缩性的计算方法,申请号:200810114466.9,授权日:2009年12月9日。
  13. 胡事民,程明明,陈韬,张松海,基于卡通片的高质量线结构提取方法,申请号:200810106664,授权日2009年9月25日。
  14. 程明明,张少甫,李文博,周瑞,仇玲,一种节能的路灯亮度随需动态调节系统及控制方法,申请号:200810018101,授权日:2012年4月25日。

Locations of visitors to this page

(Visited 159,952 times, 1 visits today)


318 Comments on "Code & Data"

Notify of