• ETRI Journal
• /
• v.42 no.1
• /
• pp.67-77
• /
• 2020

Image captioning has received significant interest in recent years, and notable results have been achieved. Most previous approaches have focused on generating visual descriptions from images, whereas a few approaches have exploited visual descriptions for image classification. This study demonstrates that a good performance can be achieved for both description generation and image classification through an end-to-end joint learning approach with a loss function, which encourages each task to reach a consensus. When given images and visual descriptions, the proposed model learns a multimodal intermediate embedding, which can represent both the textual and visual characteristics of an object. The performance can be improved for both tasks by sharing the multimodal embedding. Through a novel loss function based on class activation mapping, which localizes the discriminative image region of a model, we achieve a higher score when the captioning and classification model reaches a consensus on the key parts of the object. Using the proposed model, we established a substantially improved performance for each task on the UCSD Birds and Oxford Flowers datasets.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.2
• /
• pp.257-263
• /
• 2002

A graph embedding problem has been studied for applications of resource allocation and mapping the underlying data structure of a parallel algorithm into the interconnection architecture of massively parallel processing systems. In this paper, we consider the embedding problem of the pyramid into the regular 2-dimensional mesh interconnection network topology. We propose a new embedding function which can embed the pyramid of height N into 2$^{N}$ x2$^{N}$ 2-dimensional mesh with dilation max{2$^{N1}$-2. [3.2$^{N4}$＋1)/2, 2$^{N3}$＋2. [3.2$^{N4}$＋1)/2]}. This means an improvement in the dilation measure from 2$^{N}$ $^1$in the previous result into about (5/8) . 2$^{N1}$ under the same condition.condition.

• Journal of Korea Multimedia Society
• /
• v.17 no.4
• /
• pp.466-477
• /
• 2014

Many image hiding schemes based on least significant bit (LSB) transformation have been proposed. One of the LSB-based image hiding schemes that employs diamond encoding was proposed in 2008. In this scheme, the binary secret data is converted into base n representation, and the converted secret data is concealed in the cover image. Here, we show that this scheme has two vulnerabilities: noticeable spots in the stego-image, i.e., a non-smooth embedding result, and inefficiency caused by rough re-adjustment of falling-off-boundary value and impractical base translation. Moreover, we propose a new scheme that is efficient and produces a smooth and high quality embedding result by restricting n to power of 2 and using a sophisticated re-adjustment procedure. Our experimental results show that our scheme yields high quality stego-images and is secure against RS detection attack.

• Journal of Korea Water Resources Association
• /
• v.33 no.S1
• /
• pp.37-47
• /
• 2000

The method of delays is widely used for reconstruction chaotic attractors from experimental observations. Many studies have used a fixed delay time ${\tau}_d$ as the embedding dimension m is increased, but this is not necessarily the best choice for obtaining good convergence of the correlation dimension. Recently, some researchers have suggested that it is better to fix the delay time window ${\tau}_w$ instead. Unfortunately, ${\tau}_w$ cannot be estimated using either the autocorrelation function or the mutual information, and no standard procedure for estimating ${\tau}_w$ has yet emerged. However, a new technique, called the C-C method, can be used to estimate either ${\tau}_d\;or\;{\tau}_w$. Using this method, we show that, for small data sets, fixing ${\tau}_w$, rather than ${\tau}_d$, does indeed lead to a more rapid convergence of the correlation dimension as the embedding dimension m in increased.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2000.05a
• /
• pp.37-47
• /
• 2000

The method of delays is widely used fur reconstructing chaotic attractors from experimental observations. Many studies have used a fixed delay time ${\tau}_d$ as the embedding dimension m is increased, but this is not necessarily the best choice for obtaining good convergence of the correlation dimension. Recently, some researchers have suggested that it is better to fix the delay time window ${\tau}_w$ instead. Unfortunately, ${\tau}_w$ cannot be estimated using either the autocorrelation function or the mutual information, and no standard procedure for estimating ${\tau}_w$has yet emerged. However, a new technique, called the C-C method, can be used to estimate either ${\tau}_d{\;}or{\;}{\tau}_w$. Using this method, we show that, for small data sets, fixing ${\tau}_w$, rather than ${\tau}_d$, does indeed lead to a more rapid convergence of the correlation dimension as the embedding dimension m is increased.

• Communications of the Korean Mathematical Society
• /
• v.19 no.4
• /
• pp.661-681
• /
• 2004

We research properties of the space of measurable functions square integrable with weight exp$2\nu $\mid$x$\mid$$, and those of the space of Fourier hyperfunctions. Also we show that the several embedding theorems hold true, and that the Fourier-Lapace operator is an isomorphism of the space of strongly decreasing Fourier hyperfunctions onto the space of analytic functions extended to any strip in $C^n$ which are estimated with the aid of a special exponential function exp($\mu$｜x｜).

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.139-144
• /
• 2022

Technological advancements taken the health care industry by a storm by embedding sensors in human body to measure their vitals. These smart solutions provide better and flexible health care to patients, and also easy monitoring for the medical practitioners. However, these innovative solutions provide their own set of challenges. The major challenge faced by embedding sensors in body is the issue of lack of infinite energy source. This work presents a meta-heuristic based routing model using modified PSO, and adopts an energy harvesting scheme to improve the network lifetime. The routing process is governed by modifying the fitness function of PSO to include charge, temperature and other vital factors required for node selection. A reactive routing model is adopted to ensure reliable packet delivery. Experiments have been performed and comparisons indicate that the proposed Energy Harvesting and Modified PSO (EHMP) model demonstrates low overhead, higher network lifetime and better network stability.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.143-151
• /
• 2020

The digital content's security and authentication are important in the field of digital content application. There are some methods to perform the authentication. The digital watermarking is one of authentication methods. Paper presents a digital watermark authentication method that works in the application of digital image. The proposed watermark has the triple status information and performs the embedding and the detection without original Content. When authenticating the owner information of digital content, an autocorrelation function is used. In addition, a spread spectrum method is used to be adaptive to the signal of the original content in the frequency domain(DWT Domain). Therefore, the possibility of errors occurring in the detection of hidden information was reduced. it also has a advantage what Watermarking in DWT has faster embedding and detection time than other transformation domains(DFT, DCT, etc.). if it has a an image of size N=mXm, the computational amount can be reduced from O(N·logN) to O(N). The particular advantage is that it can hide more information(bits) per bit.

• Industrial Engineering and Management Systems
• /
• v.14 no.3
• /
• pp.312-317
• /
• 2015

The dynamic system approach in time series has been used in many real problems. Based on Taken's embedding theorem, we can build the predictive function where input is the time delay coordinates vector which consists of the lagged values of the observed series and output is the future values of the observed series. Although the time delay coordinates vector from multivariate time series brings more information than the one from univariate time series, it can exhibit statistical redundancy which disturbs the performance of the prediction function. We apply dimension reduction techniques to solve this problem and analyze the effect of this approach for prediction. Our experiment uses delayed Lorenz series; least squares support vector regression approximates the predictive function. The result shows that linearly preserving projection improves the prediction performance.

• Journal of Korea Multimedia Society
• /
• v.6 no.3
• /
• pp.508-517
• /
• 2003

This paper presents perceptual model with a stochastic multiresolution characteristic that can be applied with watermark embedding in the biorthogonal wavelet domain. The perceptual model with adaptive watermarking algorithm embeds at the texture and edge region for more strongly embedded watermark by the SSQ. The watermark embedding is based on the computation of a NVF that has local image properties. This method uses non- stationary Gaussian and stationary Generalized Gaussian models because watermark has noise properties. The particularities of embedding in the stationary GG model use shape parameter and variance of each subband regions in multiresolution. To estimate the shape parameter, we use a moment matching method. Non-stationary Gaussian model uses the local mean and variance of each subband. The experiment results of simulation were found to be excellent invisibility and robustness. Experiments of such distortion are executed by Stirmark 3.1 benchmark test.