Peyman Milanfar

Computational Vision

Recognizing visual objects in images, and actions in videos, are important problems in computer vision, with many applications in security, commerce, human-compute interaction, content-based video retrieval, visual surveillance, analysis of sports events and more. Recognition is mainly divided into two parts: category recognition (classification) and detection/localization. The goal of category recognition is to classify a given object (or action) into one of several pre-specified categories, while object (action) detection is meant to separate objects (actions) of interest from the background in a target image or video. Typically, learning-based approaches involve generative or discriminative training models (parametric models) for each category based on training examples. These methods require a large number of training examples, can result in over-fitting of parameters, and do not scale well with the number of object (or action) categories. We have developed a framework where problems such as generic object detection, action detection, and action category classification can be solved in a unified setting from a single example (i.e. without training.) In a related effort, we have also developed a method which can accurately detect salient objects or actions from visual data without any background or prior knowledge. Here is a recent talk that summarizes these ideas. For additional results and graphic explanations, please visit the project webpages for object detection; action recognition ; and saliency detection. Also, please consult the relevant publications below.

Related Journal Publications

  1. H.J. Seo and P. Milanfar, “ Action Recognition from One Example”, Accepted to IEEE Trans. on Pattern Analysis and Machine Intelligence
  2. H.J. Seo and P. Milanfar, “ Static and Space-time Visual Saliency Detection by Self-Resemblance”,  The Journal of Vision 9(12):15, 1-27,, doi:10.1167/9.12.15
  3. H.J. Seo and P. Milanfar, “ Training-free, Generic Object Detection using Locally Adaptive Regression Kernels”, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 32, no. 9, pp. 1688-1704 , Sept. 2010

Related Conference Publications and Presentations

  1. H.J. Seo, and P. Milanfar, “ Detection of Human Actions From A Single Example ”, IEEE International Conference on Computer Vision (ICCV), Kyoto, September, 2009
  2. H.J. Seo, and P. Milanfar, “ Nonparametric Bottom-Up Saliency Detection by Self-Resemblance ”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1st International Workshop on Visual Scene Understanding (ViSU’09), Miami, June, 2009
  3. H. Seo, and P. Milanfar, “ Using Local Regression Kernels for Statistical Object Detection ”, Proceedings of IEEE International Conference on Image Processing (ICIP), San Diego, CA, October 2008.