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

The Hough voting framework is a popular approach to parts based pedestrian detection. It works by allowing image features to vote for the positions and scales of pedestrians within a test image. Each vote is cast independently from other votes, which allows for strong occlusion robustness. However this approach can produce false pedestrian detections by accumulating votes inconsistent with each other, especially in cluttered scenes such as typical street scenes. This work aims to reduce the sensibility to clutter in the Hough voting framework. Our idea is to use object segmentation and object pose parameters to enforce votes’ consistency both at training and testing time. Specifically, we use segmentation and pose parameters to guide the learning of a pedestrian model able to cast mutually consistent votes. At test time, each candidate detection’s support votes are looked upon from a segmentation and pose viewpoints to measure their level of agreement. We show that this measure provides an efficient way to discriminate between true and false detections. We tested our method on four challenging pedestrian datasets. Our method shows clear improvements over the original Hough based detectors and performs on par with recent enhanced Hough based detectors. In addition, our method can perform segmentation and pose estimation as byproducts of the detection process. key words: Hough based detections, pedestrian segmentation, pose estimation, Random Forest, kPCA

http://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/192298/1/transinf.2014EDP7092.pdf

Improving Hough Based Pedestrian Detection Accuracy by Using Segmentation and Pose Subspaces

This article discusses how to realize the process of converting the user's face into an avatar's face by preserving the expression. The objective of this work is to make this process reflect the user's subjective view about correspondence between the facial images of the user and the avatar. In this article, it is proposed to adapt the process to the user's view through interactions with the user. This is realized by an example-based approach, in which the correspondence between the facial images of the user and the avatar is estimated from its examples obtained from the interactions with the user. The process increasingly reflects the user's view with the number of examples.

https://www.jstage.jst.go.jp/article/iscie1988/14/6/14_6_308/_pdf

Converting Faces by Preserving the Expression from the Actor's Viewpoint Based on Examples Obtained from User Interactions

A high speed 3D reconstruction method using multiple video cameras is presented. The video cameras are set to surround the real 3D space where people exist. Reconstructed 3D space is displayed in voxel format and a user can see the space from any viewpoint with a VR viewer. We implemented a prototype system that can work out the 3D reconstruction with the speed of 7.2 fps in 560ms delay.

/pdf/high-speed-3d-reconstruction-by-video-image-pipeline-3yusbik8am.pdf

High Speed 3D Reconstruction by Video Image Pipeline Processing And Division of Spatio-Temporal Space

Analysis of students' eye movement in relation to contents of multimedia lecture

A method to extract character strings from unformed document images, which have inclined strings of character patterns and have no structure at all, is described. To process such kinds of unformed documents, previous schemes, which are intended only to deal with such documents as have just horizontal or vertical strings of characters, do not work well. The method is based on the idea that the processes of recognition and extraction of character patterns should cooperate together, and on the characteristic that the character patterns are located close to each other when they belong to the same string and apart when they do not. The method has been implemented and the experimental results show the robustness of the method. >

Michihiko Minoh

Papers

Improving Hough Based Pedestrian Detection Accuracy by Using Segmentation and Pose Subspaces

Converting Faces by Preserving the Expression from the Actor's Viewpoint Based on Examples Obtained from User Interactions

High Speed 3D Reconstruction by Video Image Pipeline Processing And Division of Spatio-Temporal Space

Analysis of students' eye movement in relation to contents of multimedia lecture

Extraction of character strings from unformed document images