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

Analysis of transportation mode used by tourists in touristic destination areas provides basic information of tourism policy making for local governments or marketing strategy making for the tourism industry. With the technical advances of tracking devices, GPS supported smartphones sense the movement of tourists, and generate a large volumes of data which show tourists' trajectory data. Because GPS trajectory data has only latitudes, longitude and time, transportation modes should be inferred by any methods. Some researchers infer transportation modes from velocity of tourists by using machine learning like Support Vector Machine (SVM) and Conditional Random Field (CRF). However, because trains and buses temporarily stop at stations or bus stops, respectively, when movement is slow, the transportation mode can not be inferred correctly only from velocity. The locations where trains and buses temporarily stop are generally known in advance. Therefore, the transportation mode can be correctly inferred by using such location data as environmental constraints.In this research, we propose a new transportation mode inference method using environmental constraints. We assume that tourists move by foot or public transportation in the large-size touristic destinations which include many touristic spots.

https://dl.acm.org/doi/pdf/10.1145/3022227.3022309

Transportation mode inference using environmental constraints

In this paper, we propose a novel method for reconstructing the shape model of a non-rigid object. We represent the non-rigid object as the union of rigid components, and acquire range images of the object and motion of each component while the object varies its shape. We acquire the range images using one-shot scanning, and we use marker-based motion capture for motion acquisition. Based on them, our method performs registration of the range images and assigns a shape to each component. We propose the use of the Pinhole-to-Projection Pyramid obtained from each range image to non-iteratively solve the assignment task. The effectiveness of our method is demonstrated by applying it to reconstruct the shape of a human hand.

Pinhole-to-Projection Pyramid Subtraction for Reconstructing Non-rigid Objects from Range Images

We aim to extract object-handlings in real time for realizing a system supporting cooking activities. Traditional methods based solely on camera is principally poor at judging whether touched or just closed near objects, and those based on load sensing table cannot extract concurrent object-handlings separately. To extract object-handlings separately, we propose a sensor fusion framework of a camera and load sensor information. We applied our method to a simple cooking activity and confirmed that our method principally worked as expected.

Detecting start and end times of object-handlings on a table by fusion of camera and load sensors

We propose a method for acquiring a 3D shape of human body segments accurately. Using a light stripe triangulation range finder, we can acquire accurate the 3D shape of a motionless object in a dozen of seconds. If the object were to move during the scanning, the acquired shape would be distorted. Naturally, humans move slightly for making balance while standing even if the subject tries to stay still for avoiding the distortion of the shape. Our method corrects the distortion based on measured motion during the scanning

Experimental results show the accuracy of our shape measurements. Trunk swaying degrades the accuracy of the light stripe triangulation from 1mm to 10mm. We can keep the accuracy of as good as 2mm by applying our method

http://www.iiyama-lab.org/publication/amdo2006-funatomi.pdf

Michihiko Minoh

Papers

Transportation mode inference using environmental constraints

Pinhole-to-Projection Pyramid Subtraction for Reconstructing Non-rigid Objects from Range Images

Detecting start and end times of object-handlings on a table by fusion of camera and load sensors

3D shape reconstruction of trunk swaying human body segments

Evaluation of distance learning system by the student in Japan and USA