Frequency-Based Motion Representation for Video Generative Adversarial Networks.

Videos contain motions of various speeds. For example, the motions of one's head and mouth differ in terms of speed - the head being relatively stable and the mouth moving rapidly as one speaks. Despite its diverse nature, previous video GANs generate video based on a single unified motion representation without considering the aspect of speed.

Development of an Antiwindup Technique for a Cascade Control System.

A cascade control system comprising the primary and secondary controllers suffers from a cascade-type integral windup problem in which the output saturation of the secondary control loop can considerably increase the integral part of the primary control loop. In this paper, we present a new predictive antiwindup technique that can completely eliminate the possibility of secondary controller output saturation, resulting in no cascade-type integral windup phenomenon. The proposed method does not require any type of process models; thus, its implementation is simple and straightforward, which is a very favorable advantage compared to the model-based antiwindup techniques from the practical viewpoint.

Content-Aware Focal Plane Selection and Proposals for Object Tracking on Plenoptic Image Sequences.

Object tracking is a fundamental problem in computer vision since it is required in many practical applications including video-based surveillance and autonomous vehicles. One of the most challenging scenarios in the problem is when the target object is partially or even fully occluded by other objects. In such cases, most of existing trackers can fail in their task while the object is invisible.

Distance Encoded Product Quantization for Approximate K-Nearest Neighbor Search in High-Dimensional Space.

Approximate K-nearest neighbor search is a fundamental problem in computer science. The problem is especially important for high-dimensional and large-scale data. Recently, many techniques encoding high-dimensional data to compact codes have been proposed.

Spherical hashing: binary code embedding with hyperspheres.

Many binary code embedding schemes have been actively studied recently, since they can provide efficient similarity search, and compact data representations suitable for handling large scale image databases. Existing binary code embedding techniques encode high-dimensional data by using hyperplane-based hashing functions. In this paper we propose a novel hypersphere-based hashing function, spherical hashing, to map more spatially coherent data points into a binary code compared to hyperplane-based hashing functions.

Genetic variants of the FABP4 gene are associated with marbling scores and meat quality grades in Hanwoo (Korean cattle).

This study was aimed to search new genetic variants in the bovine FABP4 gene as molecular markers for meat quality and carcass traits. PCR-RFLP analysis revealed that three SNPs located at nucleotide positions g.2834C>G, g.

Genetic association of phosphodiesterase 1B (PDE1B) with carcass traits in Korean cattle.

Quantitative trait loci for fat deposition and carcass traits have been identified in the vicinity of the gene encoding phosphodiesterase 1B (PDE1B) on bovine chromosome 5. Therefore, the PDE1B gene can be considered as a positional and functional candidate gene for carcass traits in beef cattle. This study aimed to identify single nucleotide polymorphisms (SNPs) in the PDE1B gene and to evaluate their associations with carcass traits in Korean cattle.