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

This paper describes our work in computer vision to track food materials in the food preparation process. Tracking such food materials is difficult, because they are often hidden when moved by hand. Furthermore, their appearance may change in hand when they are cut or peeled. For tracking these objects in such situations, we propose a novel method that matches an object on a cooking table to one grasped in the past. We use the following three criteria to match the objects even when they are cut or peeled: the similarity in their appearance, the validity of their change in appearance, and the grasped order. We experimentally evaluated our method by applying it to the scenes of cutting and peeling food materials. As a result, we achieved an accuracy of 83.6% in matching the objects.

http://www.mm.media.kyoto-u.ac.jp/old/research/doc/991/PID1495591.pdf

Tracking Food Materials with Changing Their Appearance in Food Preparing

A physically based environment of Artificial RealiTY for dress simulation (PARTY) which shows fully dressed humans in various environments is described. In PARTY, a dynamically deformable cloth model of a dress plays the central role. This paper proposes a new dynamically deformable cloth model that can handle actual nonlinear kinetic properties of cloth measured by mechanical experiments, and also propose a numerical method appropriate for PARTY. The numerical results of the Drape Test are compared with the shape of real cloth in experiments.

PARTY: A numerical calculation method for a dynamically deformable cloth model

Person reidentification tackles the problem of building a correspondence between different images of the same person captured by distributed cameras. To date, attempts to solve this problem have focused on either feature representation or learning methods. Usually, the greater the number of the samples for each person, the better the reidentification performance is. However, in the real world, we may not be able to acquire enough samples to give acceptable performance. Here, we focus on the so-called “single-shot versus single-shot” problem: matching one image of a person to another. Because of the extremely small sample class size, there is limited scope to statistically weaken the empirical risk for hand-crafted feature representation. Therefore, we resort to metric learning methods, such as the ranking-specialized metric learning to rank (MLR) and the classification-based maximally collapsing metric learning (MCML). Taking advantage of the complementarity between them, we propose a novel “coupled metric learning” approach. This searches for the optimal linear projection for the original feature space using MCML before minimizing the ranking loss via MLR. Experiments on widely used benchmark datasets show encouraging results.

https://www.spiedigitallibrary.org/journals/optical-engineering/volume-52/issue-2/027203/Coupled-metric-learning-for-single-shot-versus-single-shot-person/10.1117/1.OE.52.2.027203.pdf

Coupled metric learning for single-shot versus single-shot person reidentification

Person re-identification is becoming a hot research topic due to its academic importance and attractive applications in visual surveillance. This paper focuses on solving the relatively harder and more importance multiple-shot re-identification problem. Following the idea of treating it as a set-based classification problem, we propose a new model called Locality-constrained Collaborative Sparse Approximation (LCSA) which is made to be as efficient, effective and robust as possible. It improves the very recently proposed Collaborative Sparse Approximation (CSA) model by introducing two types of locality constraints to enhance the quality of the data for collaborative approximation. Extensive experiments demonstrate that LCSA is not only much better than CSA in terms of effectiveness and robustness, but also superior to other related methods.

Locality-Constrained Collaborative Sparse Approximation for Multiple-Shot Person Re-identification

Person re-identification concerns about the problem of recognizing people across space (captured by different cameras) and/or over time gaps. Though recently the literature on it grows rapidly, all the proposed solutions have treated it as a normal classification or ranking problem. In this paper, however, we argue that it is in fact a natural transfer learning problem, thus it's valuable and also necessary to investigate how the progress on transfer learning could benefit the research on it. We present so far the first study on justifying the effectiveness of a representative transfer learning methodology: feature-based inductive transfer learning, for person re-identification. Extensive experiments on standard datasets with typical methods result in several important findings.

Michihiko Minoh

Papers

Tracking Food Materials with Changing Their Appearance in Food Preparing

PARTY: A numerical calculation method for a dynamically deformable cloth model

Coupled metric learning for single-shot versus single-shot person reidentification

Locality-Constrained Collaborative Sparse Approximation for Multiple-Shot Person Re-identification

Can feature-based inductive transfer learning help person re-identification?