arXiv subjects

Jaeyoung Choi

Publications and source records attributed to Jaeyoung Choi.

At least 19 recordsLinked to original sources

arXiv2026

Null-Space Diffusion Restoration with Adaptive Uncertainty-Guided Fusion for Ultrasound Speckle Reduction

Ultrasound B-mode imaging commonly suffers from speckle noise and artifacts, requiring a delicate balance between contrast, resolution, and preservation of anatomical structures. Although recently developed despeckling methods have achieved some progress, supervised learning approaches remain fundamentally limited by the ground truth paradox, which arises from the absence of noise-free, ground truth reference images in in vivo scenarios. Existing unsupervised diffusion-based methods typically enforce data consistency directly in the nonlinear log-compressed domain, which can disproportionately amplify background artifacts when mapped back to the envelope domain. To overcome these limitations, we propose an uncertainty-guided null-space diffusion (UGNS) framework, a novel label-free solution that enforces consistency correction on a stabilized positive-envelope proxy obtained via inverse log compression. The proposed UGNS introduces several technical novelties: (a) extraction of a structural prior in the stabilized envelope domain to produce a robust signal envelope that preserves anatomical structure, (b) development of an adaptive range-null reconstruction mechanism that uses an adaptive weight mask to preserve tissue regions via range-space projection, and (c) introduction of uncertainty-guided fusion in an adaptive way to mitigate sampling variability. Extensive and comparative experiments were conducted using the PICMUS benchmark and in vivo datasets. The results demonstrate that UGNS achieves competitive generalized contrast-to-noise ratio (gCNR) values across diverse datasets. In addition, it is successfully validated that UGNS effectively suppresses speckle noise while preserving fine spatial resolution. Code is available at https://github.com/yousirong/UGNS.git.

cs.CV↗

arXiv2026

EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting

Forecasting future 3D hand pose sequences from egocentric video is essential for understanding human intention and enabling embodied applications such as AR/VR assistance and human-robot interaction. However, this task remains a highly challenging problem because egocentric hand motion is driven by complex human intent, exhibits highly dexterous articulations, and is observed under drastic viewpoint shifts induced by ego-motion. In this work, we introduce EggHand, a foundation-model-based framework for egocentric hand pose forecasting that unifies multimodal semantic reasoning with dynamic motion modeling. Our approach couples an action decoder from a Vision-Language-Action (VLA) model, which captures the structured temporal dynamics of hand motion, with an egocentric video-text encoder that provides viewpoint-aware contextual information learned from large-scale first-person video. Together, these components overcome the brittleness of generic visual encoders under ego-motion and enable joint reasoning over motion, context, and high-level intent-without relying on body pose or external tracking. Experiments on the EgoExo4D dataset show that EggHand sets a new state of the art in forecasting accuracy, remains robust under severe ego-motion, and further enables controllable prediction via language-based task prompts. Project page: https://jyoun9.github.io/EggHand

cs.CV↗

arXiv2025

Hybrid GCN-GRU Model for Anomaly Detection in Cryptocurrency Transactions

Blockchain transaction networks are complex, with evolving temporal patterns and inter-node relationships. To detect illicit activities, we propose a hybrid GCN-GRU model that captures both structural and sequential features. Using real Bitcoin transaction data (2020-2024), our model achieved 0.9470 Accuracy and 0.9807 AUC-ROC, outperforming all baselines.

cs.LG↗

arXiv2025

Injectivity radius lower bound of convex sum of tame Riemannian metrics and applications to symplectic topology

Motivated by the aspect of large-scale symplectic topology, we prove that for any pair $g_0, \, g_1$ of complete Riemannian metrics of bounded curvature and \emph{of injectivity radius bounded away from zero}, the convex sum $g_s: = (1-s ) g_0 + s g_1$ also has bounded curvature depending only on the curvature bounds $\|R_{g_i}\|_{C^0}$ of $g_0$ or $g_1$, and that the injectivity radii of $g_s$ have uniform lower bound depending only on the derivative bounds $\|R_{g_i}\|_{C^1} = \|R_{g_i}\|_{C^0} + \|DR_{g_i}\|_{C^0}$. A main technical ingredient to establish the injectivity radius lower bound is an application of the quantitative inverse function theorem. Using these estimates, we prove that each quasi-isometry class of tame metrics is convex and so contractible in strong $C^r$ topology for all finite regularity class of $3 \leq r < \infty$. Using this Riemannian geometry result, we prove that the set of $C^3$-tame almost complex structures inside the same quasi-isometry class associated to the symplectic form $ω$ is contractible.

math.DG↗

arXiv2025

A Study on the Refining Handwritten Font by Mixing Font Styles

Handwritten fonts have a distinct expressive character, but they are often difficult to read due to unclear or inconsistent handwriting. FontFusionGAN (FFGAN) is a novel method for improving handwritten fonts by combining them with printed fonts. Our method implements generative adversarial network (GAN) to generate font that mix the desirable features of handwritten and printed fonts. By training the GAN on a dataset of handwritten and printed fonts, it can generate legible and visually appealing font images. We apply our method to a dataset of handwritten fonts and demonstrate that it significantly enhances the readability of the original fonts while preserving their unique aesthetic. Our method has the potential to improve the readability of handwritten fonts, which would be helpful for a variety of applications including document creation, letter writing, and assisting individuals with reading and writing difficulties. In addition to addressing the difficulties of font creation for languages with complex character sets, our method is applicable to other text-image-related tasks, such as font attribute control and multilingual font style transfer.

cs.CV↗

arXiv2025

Text-Conditioned Diffusion Model for High-Fidelity Korean Font Generation

Automatic font generation (AFG) is the process of creating a new font using only a few examples of the style images. Generating fonts for complex languages like Korean and Chinese, particularly in handwritten styles, presents significant challenges. Traditional AFGs, like Generative adversarial networks (GANs) and Variational Auto-Encoders (VAEs), are usually unstable during training and often face mode collapse problems. They also struggle to capture fine details within font images. To address these problems, we present a diffusion-based AFG method which generates high-quality, diverse Korean font images using only a single reference image, focusing on handwritten and printed styles. Our approach refines noisy images incrementally, ensuring stable training and visually appealing results. A key innovation is our text encoder, which processes phonetic representations to generate accurate and contextually correct characters, even for unseen characters. We used a pre-trained style encoder from DG FONT to effectively and accurately encode the style images. To further enhance the generation quality, we used perceptual loss that guides the model to focus on the global style of generated images. Experimental results on over 2000 Korean characters demonstrate that our model consistently generates accurate and detailed font images and outperforms benchmark methods, making it a reliable tool for generating authentic Korean fonts across different styles.

cs.CV↗

arXiv2025

Detection of Rumors and Their Sources in Social Networks: A Comprehensive Survey

With the recent advancements in social network platform technology, an overwhelming amount of information is spreading rapidly. In this situation, it can become increasingly difficult to discern what information is false or true. If false information proliferates significantly, it can lead to undesirable outcomes. Hence, when we receive some information, we can pose the following two questions: $(i)$ Is the information true? $(ii)$ If not, who initially spread that information? % The first problem is the rumor detection issue, while the second is the rumor source detection problem. A rumor-detection problem involves identifying and mitigating false or misleading information spread via various communication channels, particularly online platforms and social media. Rumors can range from harmless ones to deliberately misleading content aimed at deceiving or manipulating audiences. Detecting misinformation is crucial for maintaining the integrity of information ecosystems and preventing harmful effects such as the spread of false beliefs, polarization, and even societal harm. Therefore, it is very important to quickly distinguish such misinformation while simultaneously finding its source to block it from spreading on the network. However, most of the existing surveys have analyzed these two issues separately. In this work, we first survey the existing research on the rumor-detection and rumor source detection problems with joint detection approaches, simultaneously. % This survey deals with these two issues together so that their relationship can be observed and it provides how the two problems are similar and different. The limitations arising from the rumor detection, rumor source detection, and their combination problems are also explained, and some challenges to be addressed in future works are presented.

cs.SI↗

arXiv2024

CiFHER: A Chiplet-Based FHE Accelerator with a Resizable Structure

Fully homomorphic encryption (FHE) is in the spotlight as a definitive solution for privacy, but the high computational overhead of FHE poses a challenge to its practical adoption. Although prior studies have attempted to design ASIC accelerators to mitigate the overhead, their designs require excessive chip resources (e.g., areas) to contain and process massive data for FHE operations. We propose CiFHER, a chiplet-based FHE accelerator with a resizable structure, to tackle the challenge with a cost-effective multi-chip module (MCM) design. First, we devise a flexible core architecture whose configuration is adjustable to conform to the global organization of chiplets and design constraints. Its distinctive feature is a composable functional unit providing varying computational throughput for the number-theoretic transform, the most dominant function in FHE. Then, we establish generalized data mapping methodologies to minimize the interconnect overhead when organizing the chips into the MCM package in a tiled manner, which becomes a significant bottleneck due to the packaging constraints. This study demonstrates that a CiFHER package composed of a number of compact chiplets provides performance comparable to state-of-the-art monolithic ASIC accelerators while significantly reducing the package-wide power consumption and manufacturing cost.

cs.AR↗

arXiv2023

Twitter Attribute Classification with Q-Learning on Bitcoin Price Prediction

Aspiring to achieve an accurate Bitcoin price prediction based on people's opinions on Twitter usually requires millions of tweets, using different text mining techniques (preprocessing, tokenization, stemming, stop word removal), and developing a machine learning model to perform the prediction. These attempts lead to the employment of a significant amount of computer power, central processing unit (CPU) utilization, random-access memory (RAM) usage, and time. To address this issue, in this paper, we consider a classification of tweet attributes that effects on price changes and computer resource usage levels while obtaining an accurate price prediction. To classify tweet attributes having a high effect on price movement, we collect all Bitcoin-related tweets posted in a certain period and divide them into four categories based on the following tweet attributes: $(i)$ the number of followers of the tweet poster, $(ii)$ the number of comments on the tweet, $(iii)$ the number of likes, and $(iv)$ the number of retweets. We separately train and test by using the Q-learning model with the above four categorized sets of tweets and find the best accurate prediction among them. Especially, we design several reward functions to improve the prediction accuracy of the Q-leaning. We compare our approach with a classic approach where all Bitcoin-related tweets are used as input data for the model, by analyzing the CPU workloads, RAM usage, memory, time, and prediction accuracy. The results show that tweets posted by users with the most followers have the most influence on a future price, and their utilization leads to spending 80\% less time, 88.8\% less CPU consumption, and 12.5\% more accurate predictions compared with the classic approach.

cs.SI↗

arXiv2023

Permanence based Hidden Community and Graph Recovery in Social Networks

Due to the recent development of data analysis techniques, technologies for detecting communities through information expressed in social networks have been developed. Although it has several advantages, including the ability to effectively share recommended items through an estimated community, it may cause personal privacy issues. Therefore, recently, the problem of hiding the real community well is being studied at the same time. As an example, Mittal \etal, proposed an algorithm called NEURAL that can hide this community well based on a metric called permanence. Based on this, in this study, we propose a Reverse NEURAL (R-NEURAL) algorithm that restores the community as well as the original graph structure using permanence. The proposed algorithm includes a method for well restoring not only the community hidden by the NEURAL algorithm but also the original graph structure modified by recovered edges. We conduct experiments on real-world graphs and found that the proposed algorithm recovers well the hidden community as well as the graph structure.

cs.SI↗

arXiv2023

Fukaya category of infinite-type surfaces

In this paper, we construct a Fukaya category of any infinite type surface whose objects are gradient sectorial Lagrangians. This class of Lagrangian submanifolds is introduced by one of the authors in [Oh21b] which can serve as an object of a Fukaya category of any Liouville manifold that admits an exhausting proper Morse function, in particular on the Riemann surface of infinite type. We describe a generating set of the Fukaya category in terms of the end structure of the surface when the surface has countably many limit points in its ideal boundary, the latter of which can be described in terms of a subset of the Cantor set. We also show that our Fukaya category is not quasi-equivalent to the limit of the Fukaya category of surfaces of finite type appearing in the literature.

math.SG↗

arXiv2022

Dynamic RF Beam Codebook Reduction for Cost-Efficient mmWave Full-Duplex Systems

The recent attempts to realize full-duplex (FD) communications in millimeter wave (mmWave) systems have garnered a significant amount of interest for its potential. In this paper, we present a cost-efficient design of mmWave FD systems, where the system dynamically reduces the RF beam codebook in a computationally efficient manner, so that it is comprised of the RF beams that will prevent the Rx receive chain from saturating due to the self-interference (SI). The analog beamformer will suppress the SI to the level that the residual SI can be completely removed with digital SI cancellation, allowing the digital beamformer to concentrate on the desired channel, free of the SI. To reduce the computation required for the proposed method, we propose two sufficient conditions that prevent the Rx side saturations, which are practically tight. Through performance valuations conducted in realistically modeled mmWave FD scenarios, we demonstrate that the proposed design achieves comparable performance with the ideal FD and other benchmarks with significantly lower costs.

eess.SP↗

arXiv2022

Sequential Movie Genre Prediction using Average Transition Probability with Clustering

In recent movie recommendations, predicting the user's sequential behavior and suggesting the next movie to watch is one of the most important issues. However, capturing such sequential behavior is not easy because each user's short-term or long-term behavior must be taken into account. For this reason, many research results show that the performance of recommending a specific movie is not very high in a sequential recommendation. In this paper, we propose a cluster-based method for classifying users with similar movie purchase patterns and a movie genre prediction algorithm rather than the movie itself considering their short-term and long-term behaviors. The movie genre prediction does not recommend a specific movie, but it predicts the genre for the next movie to watch in consideration of each user's preference for the movie genre based on the genre included in the movie. Through this, it is possible to provide appropriate guidelines for recommending movies including the genre to users who tend to prefer a specific genre. In particular, in this paper, users with similar genre preferences are organized into clusters to recommend genres, and in clusters that do not have relatively specific tendencies, genre prediction is performed by appropriately trimming genres that are not necessary for recommendation in order to improve performance. We evaluate our method on well-known movie datasets, and qualitatively that it captures personalized dynamics and is able to make meaningful recommendations.

cs.IR↗

arXiv2022

FontNet: Closing the gap to font designer performance in font synthesis

Font synthesis has been a very active topic in recent years because manual font design requires domain expertise and is a labor-intensive and time-consuming job. While remarkably successful, existing methods for font synthesis have major shortcomings; they require finetuning for unobserved font style with large reference images, the recent few-shot font synthesis methods are either designed for specific language systems or they operate on low-resolution images which limits their use. In this paper, we tackle this font synthesis problem by learning the font style in the embedding space. To this end, we propose a model, called FontNet, that simultaneously learns to separate font styles in the embedding space where distances directly correspond to a measure of font similarity, and translates input images into the given observed or unobserved font style. Additionally, we design the network architecture and training procedure that can be adopted for any language system and can produce high-resolution font images. Thanks to this approach, our proposed method outperforms the existing state-of-the-art font generation methods on both qualitative and quantitative experiments.

cs.CV↗

arXiv2020

Rumor Source Detection under Querying with Untruthful Answers

Social networks are the major routes for most individuals to exchange their opinions about new products, social trends and political issues via their interactions. It is often of significant importance to figure out who initially diffuses the information, ie, finding a rumor source or a trend setter. It is known that such a task is highly challenging and the source detection probability cannot be beyond 31 percent for regular trees, if we just estimate the source from a given diffusion snapshot. In practice, finding the source often entails the process of querying that asks "Are you the rumor source?" or "Who tells you the rumor?" that would increase the chance of detecting the source. In this paper, we consider two kinds of querying: (a) simple batch querying and (b) interactive querying with direction under the assumption that queries can be untruthful with some probability. We propose estimation algorithms for those queries, and quantify their detection performance and the amount of extra budget due to untruthfulness, analytically showing that querying significantly improves the detection performance. We perform extensive simulations to validate our theoretical findings over synthetic and real-world social network topologies.

cs.SI↗

arXiv2020

Information Source Finding in Networks: Querying with Budgets

In this paper, we study a problem of detecting the source of diffused information by querying individuals, given a sample snapshot of the information diffusion graph, where two queries are asked: {\em (i)} whether the respondent is the source or not, and {\em (ii)} if not, which neighbor spreads the information to the respondent. We consider the case when respondents may not always be truthful and some cost is taken for each query. Our goal is to quantify the necessary and sufficient budgets to achieve the detection probability $1-δ$ for any given $0<δ<1.$ To this end, we study two types of algorithms: adaptive and non-adaptive ones, each of which corresponds to whether we adaptively select the next respondents based on the answers of the previous respondents or not. We first provide the information theoretic lower bounds for the necessary budgets in both algorithm types. In terms of the sufficient budgets, we propose two practical estimation algorithms, each of non-adaptive and adaptive types, and for each algorithm, we quantitatively analyze the budget which ensures $1-δ$ detection accuracy. This theoretical analysis not only quantifies the budgets needed by practical estimation algorithms achieving a given target detection accuracy in finding the diffusion source, but also enables us to quantitatively characterize the amount of extra budget required in non-adaptive type of estimation, refereed to as {\em adaptivity gap}. We validate our theoretical findings over synthetic and real-world social network topologies.

cs.SI↗

arXiv2020

DIME: An Online Tool for the Visual Comparison of Cross-Modal Retrieval Models

Cross-modal retrieval relies on accurate models to retrieve relevant results for queries across modalities such as image, text, and video. In this paper, we build upon previous work by tackling the difficulty of evaluating models both quantitatively and qualitatively quickly. We present DIME (Dataset, Index, Model, Embedding), a modality-agnostic tool that handles multimodal datasets, trained models, and data preprocessors to support straightforward model comparison with a web browser graphical user interface. DIME inherently supports building modality-agnostic queryable indexes and extraction of relevant feature embeddings, and thus effectively doubles as an efficient cross-modal tool to explore and search through datasets.

cs.MM↗

arXiv2020

Necessary and Sufficient Budgets in Information Source Finding with Querying: Adaptivity Gap

cs.SI↗