Visual Computing--Microsoft group

Visual Computing

Overview

Computer Vision is an exciting new research area that studies how to make computers efficientlyperceive, process, and understand visual data such as images and videos. The ultimate goal is for computers to emulate the striking perceptual capability of human eyes and brains, or even to surpass and assist the human in certain ways. The Visual Computing Group at Microsoft Research Asia consists of an elite team of researchers and engineers whose expertise spans the entire spectrum of research topics in computer vision, from mathematical theory to practical applications, from physical systems to software development, and from low-level image processing to high-level image understanding. Research results from our group have made fundamental impacts on many important applications such as New High-Resolution Cameras, Face Recognition, Image Search, Virtual Earth, and Graphics & Games.

More specifically, our research activities are centered around several main research thrusts:

  1. Imaging and Photogrammetry, including high-resolution cameras, radiometric calibration, photometric stereos, 3D imaging and video, and image and video enhancement.
  2. Pattern Recognition and Statistical Learning, including data clustering and classification, manifold learning, and high-dimensional geometry and statistics.
  3. Object Detection and Recognition, including face detection, alignment, and tagging, video-based face recognition, and sparsity-based robust face recognition.
  4. Dynamical Vision, including object tracking, video motion analysis and edition, video summarization, video motion and object segmentation, dynamical photometric stereo.
  5. Interactive and Internet Vision, including interactive image segmentation, completion, and normal reconstruction, and image search and re-ranking, and large scale image and object retrieval, large volume of images visualization.

We are constantly looking for top researchers in the above areas to join our group at all levels. Please contact the group manager Yi Ma if interested.

Group News & Activities:

  • Tutorial on  Robust PCA and its Applications by John, Zhouchen, and Yi at International Conference on Image Processing, Hongkong, September 2010.
  • Tutorial on  Photometric Stereo by Yasuyuki, Bennett, and Moshe at International Conference on Image Processing, Hongkong, September 2010.
  • The group manager Yi Ma was interviewed by CNN about an article " Why Face Recognition isn't Scary -- yet." July 9, 2010
  • Our group has  15 papers published at the IEEE international conference on Computer Vision and Pattern Recognition (CVPR), June 2010.
  • The group manager Yi Ma gave  the plenary speech at the international conference on Visual Communications and Image Processing, July 2010. 
  • Microsoft Research featured story " Yi Ma and the Blessing of Dimensionality." May 28, 2010.
  • new giga-pixel digital camera is developed by our researcher Moshe Ben-Ezra.
e last few years have witnessed fast development on dictionary learning approaches for a set of visual computing tasks, largely due to their utilization in developing new techniques based on sparse representation. Compared with conventional techniques employing manually defined dictionaries, such as Fourier Transform and Wavelet Transform, dictionary learning aims at ob- taining a dictionary adaptively from the data so as to support optimal sparse representation of the data. In contrast to conventional clustering algorithms like K-means, where a data point is associated with only one cluster center, in a dictionary-based representation, a data point can be associated with a small set of dictionary atoms. us, dictionary learning provides a more flexi- ble representation of data and may have the potential to capture more relevant features from the original feature space of the data. One of the early algorithms for dictionary learning is K-SVD. In recent years, many variations/extensions of K-SVD and other new algorithms have been pro- posed, with some aiming at adding discriminative capability to the dictionary, and some attempt- ing to model the relationship of multiple dictionaries. One prominent application of dictionary learning is in the general field of visual computing, where long-standing challenges have seen promising new solutions based on sparse representation with learned dictionaries. With a timely review of recent advances of dictionary learning in visual computing, covering the most recent literature with an emphasis on papers after 2008, this book provides a systematic presentation of the general methodologies, specific algorithms, and examples of applications for those who wish to have a quick start on this subject.
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值