Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Color image segmentation: advances and prospects

When considering person re-identification (re-ID) as a retrieval process, re-ranking is a critical step to improve its accuracy. Yet in the re-ID community, limited effort has been devoted to re-ranking, especially those fully automatic, unsupervised solutions. In this paper, we propose a k-reciprocal encoding method to re-rank the re-ID results. Our hypothesis is that if a gallery image is similar to the probe in the k-reciprocal nearest neighbors, it is more likely to be a true match. Specifically, given an image, a k-reciprocal feature is calculated by encoding its k-reciprocal nearest neighbors into a single vector, which is used for re-ranking under the Jaccard distance. The final distance is computed as the combination of the original distance and the Jaccard distance. Our re-ranking method does not require any human interaction or any labeled data, so it is applicable to large-scale datasets. Experiments on the large-scale Market-1501, CUHK03, MARS, and PRW datasets confirm the effectiveness of our method.

/pdf/re-ranking-person-re-identification-with-k-reciprocal-3erzmilgv1.pdf

Re-ranking Person Re-identification with k-Reciprocal Encoding

Constructing a full-support online project-based learning environment

Most vision-based 3D acquisition methods including both passive and active methods have a limitation in that cameras must be able to observe the surface to be measured. If this is not possible, that is to say, if the surface is occluded, most of the methods cannot acquire the surface shape. In this paper, we present a method that can acquire the 3D points on the occluded surfaces. The main idea is to observe the scattering of reflected light in a participating medium instead of observing only the reflected light. We place the target in a participating medium, specifically a liquid tank filled with a participating medium, and irradiate a laser beam on it. Even if the reflecting point is occluded, our method can acquire the 3D position of occluded reflecting points from the scattering. Experimental results showed that our method can measure 3D reflecting points on several objects even if the objects are completely occluded.

http://www.iiyama-lab.org/publication/icpr2014-iiyama.pdf

3D Acquisition of Occluded Surfaces from Scattering in Participating Media

This study attempts to find a theoretical basis for the development of digital cities. The ultimate function of a digital city is to support navigation in an environment. Navigation builds on meanings of the environment resulted from semiosis processes. These processes may affect each other when combined so that become able to communicate. Communication is performed with signs and depends on the behavioral co-ordination of communicating parties. The classical theories do not satisfactory explain communication. The paper introduces a new model of communication appropriate for computer treatment.

A Semiotic Model of Communication and Its Implications for the Digital City Development

This sketch describes three dimensional (3D) computer graphics (CG) produced to illustrate the development of a human embryo for education in embryology, which is one of the basic subjects in professional medical education (Fig. 1). Although similar CG have already been produced for TV programs, they are insufficient in precision for professional medical education.

Computer graphics to illustrate the development of a human embryo for professional medical education

Recently, there are many lecture archiving system that provide lecture video, presentation slide and written text/figure on whiteboard. However, the contents of lecture archiving system are decided by the provider of the service. In this paper, we propose a new lecture archiving method based on students’ viewpoint. Our archiving method adopts the viewpoint that the majority of students are watching. We conduct verification of our proposal method, by preliminary experiment. Furthermore, we consider that our acquisition technology of lecturer and student action helps lecturers to recognize students’ ROI (Region of Interest) in

Michihiko Minoh

Papers

Constructing a full-support online project-based learning environment

3D Acquisition of Occluded Surfaces from Scattering in Participating Media

A Semiotic Model of Communication and Its Implications for the Digital City Development

Computer graphics to illustrate the development of a human embryo for professional medical education

Study on Acquisition of Lecturer and Students Actions in the Classroom.