Search Results for author: Sunwoo Kim

Found 28 papers, 9 papers with code

Classification of Edge-dependent Labels of Nodes in Hypergraphs

1 code implementation5 Jun 2023 Minyoung Choe, Sunwoo Kim, Jaemin Yoo, Kijung Shin

Interestingly, many real-world systems modeled as hypergraphs contain edge-dependent node labels, i. e., node labels that vary depending on hyperedges.

Classification Node Clustering

User-friendly Image Editing with Minimal Text Input: Leveraging Captioning and Injection Techniques

no code implementations5 Jun 2023 Sunwoo Kim, Wooseok Jang, Hyunsu Kim, Junho Kim, Yunjey Choi, Seungryong Kim, Gayeong Lee

From the users' standpoint, prompt engineering is a labor-intensive process, and users prefer to provide a target word for editing instead of a full sentence.

Prompt Engineering

DiffMatch: Diffusion Model for Dense Matching

1 code implementation30 May 2023 Jisu Nam, Gyuseong Lee, Sunwoo Kim, Hyeonsu Kim, Hyoungwon Cho, Seyeon Kim, Seungryong Kim

The objective for establishing dense correspondence between paired images consists of two terms: a data term and a prior term.


Semantic-Preserving Augmentation for Robust Image-Text Retrieval

no code implementations10 Mar 2023 Sunwoo Kim, Kyuhong Shim, Luong Trung Nguyen, Byonghyo Shim

Image text retrieval is a task to search for the proper textual descriptions of the visual world and vice versa.

Retrieval Text Retrieval

RIS-Enabled and Access-Point-Free Simultaneous Radio Localization and Mapping

no code implementations14 Dec 2022 Hyowon Kim, Hui Chen, Musa Furkan Keskin, Yu Ge, Kamran Keykhosravi, George C. Alexandropoulos, Sunwoo Kim, Henk Wymeersch

In the upcoming sixth generation (6G) of wireless communication systems, reconfigurable intelligent surfaces~(RISs) are regarded as one of the promising technological enablers, which can provide programmable signal propagation.

MmWave Mapping and SLAM for 5G and Beyond

no code implementations29 Nov 2022 Yu Ge, Ossi Kaltiokallio, Hyowon Kim, Jukka Talvitie, Sunwoo Kim, Lennart Svensson, Mikko Valkama, Henk Wymeersch

We distinguish the different types of sensing problems and then focus on mapping and SLAM as running examples.

Simultaneous Localization and Mapping

Controllable Style Transfer via Test-time Training of Implicit Neural Representation

1 code implementation14 Oct 2022 Sunwoo Kim, Youngjo Min, Younghun Jung, Seungryong Kim

We propose a controllable style transfer framework based on Implicit Neural Representation that pixel-wisely controls the stylized output via test-time training.

Model Optimization Style Transfer +1

LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data

1 code implementation CVPR 2023 JiHye Park, Sunwoo Kim, Soohyun Kim, Seokju Cho, Jaejun Yoo, Youngjung Uh, Seungryong Kim

Existing techniques for image-to-image translation commonly have suffered from two critical problems: heavy reliance on per-sample domain annotation and/or inability of handling multiple attributes per image.

Translation Unsupervised Image-To-Image Translation

REVECA -- Rich Encoder-decoder framework for Video Event CAptioner

1 code implementation18 Jun 2022 Jaehyuk Heo, YongGi Jeong, Sunwoo Kim, Jaehee Kim, Pilsung Kang

We designed a Rich Encoder-decoder framework for Video Event CAptioner (REVECA) that utilizes spatial and temporal information from the video to generate a caption for the corresponding the event boundary.

Semantic Segmentation Video Understanding

PMBM-based SLAM Filters in 5G mmWave Vehicular Networks

no code implementations5 May 2022 Hyowon Kim, Karl Granström, Lennart Svensson, Sunwoo Kim, Henk Wymeersch

Secondly, the Poisson multi-Bernoulli (PMB) SLAM filter is based on the standard reduction from PMBM to PMB, but involves a novel interpretation based on auxiliary variables and a relation to Bethe free energy.

Simultaneous Localization and Mapping

Deep Translation Prior: Test-time Training for Photorealistic Style Transfer

1 code implementation12 Dec 2021 Sunwoo Kim, Soohyun Kim, Seungryong Kim

Recent techniques to solve photorealistic style transfer within deep convolutional neural networks (CNNs) generally require intensive training from large-scale datasets, thus having limited applicability and poor generalization ability to unseen images or styles.

Style Transfer Test +1

BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancement

no code implementations17 Nov 2021 Sunwoo Kim, Minje Kim

In this paper, we present a blockwise optimization method for masking-based networks (BLOOM-Net) for training scalable speech enhancement networks.

Speech Enhancement

A Computationally Efficient EK-PMBM Filter for Bistatic mmWave Radio SLAM

no code implementations8 Sep 2021 Yu Ge, Ossi Kaltiokallio, Hyowon Kim, Fan Jiang, Jukka Talvitie, Mikko Valkama, Lennart Svensson, Sunwoo Kim, Henk Wymeersch

Millimeter wave (mmWave) signals are useful for simultaneous localization and mapping (SLAM), due to their inherent geometric connection to the propagation environment and the propagation channel.

Simultaneous Localization and Mapping

Location-aware Channel Estimation for RIS-aided mmWave MIMO Systems via Atomic Norm Minimization

no code implementations20 Jul 2021 Hyeonjin Chung, Sunwoo Kim

The beam training overhead at the base station (BS) is reduced by the direct beam steering towards the RIS with the location of the BS and the RIS.

Atomic Norm Minimization-based Low-Overhead Channel Estimation for RIS-aided MIMO Systems

no code implementations20 Jul 2021 Hyeonjin Chung, Sunwoo Kim

Pilot signals received during beam training are compiled into one matrix to define the atomic norm of the channel for RIS-aided MIMO systems.

Personalized Federated Learning over non-IID Data for Indoor Localization

no code implementations9 Jul 2021 Peng Wu, Tales Imbiriba, Junha Park, Sunwoo Kim, Pau Closas

Localization and tracking of objects using data-driven methods is a popular topic due to the complexity in characterizing the physics of wireless channel propagation models.

Indoor Localization Personalized Federated Learning

Dirichlet process approach for radio-based simultaneous localization and mapping

no code implementations2 Jul 2021 Jaebok Lee, Hyowon Kim, Henk Wymeersch, Sunwoo Kim

By comparing the results with the SLAM based on the Rao-Blackwellized probability hypothesis density filter, we confirm a slight drop in SLAM performance, but as a result, we validate that it has a significant gain in computational complexity.

Clustering Simultaneous Localization and Mapping

Cooperative mmWave PHD-SLAM with Moving Scatterers

no code implementations22 Jun 2021 Hyowon Kim, Jaebok Lee, Yu Ge, Fan Jiang, Sunwoo Kim, Henk Wymeersch

Using the multiple-model (MM) probability hypothesis density (PHD) filter, millimeter wave (mmWave) radio simultaneous localization and mapping (SLAM) in vehicular scenarios is susceptible to movements of objects, in particular vehicles driving in parallel with the ego vehicle.

Simultaneous Localization and Mapping

Test-Time Adaptation Toward Personalized Speech Enhancement: Zero-Shot Learning with Knowledge Distillation

no code implementations8 May 2021 Sunwoo Kim, Minje Kim

In addition, since the compact personalized models can outperform larger general-purpose models, we claim that the proposed method performs model compression with no loss of denoising performance.

Denoising Knowledge Distillation +5

Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification

no code implementations5 Apr 2021 Aswin Sivaraman, Sunwoo Kim, Minje Kim

Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user.

Data Augmentation Denoising +3

Deep Learning-based Beam Tracking for Millimeter-wave Communications under Mobility

no code implementations19 Feb 2021 Sun Hong Lim, Sunwoo Kim, Byonghyo Shim, Jun Won Choi

In this paper, we propose a deep learning-based beam tracking method for millimeter-wave (mmWave)communications.

Online Exemplar Fine-Tuning for Image-to-Image Translation

no code implementations18 Nov 2020 Taewon Kang, Soohyun Kim, Sunwoo Kim, Seungryong Kim

Existing techniques to solve exemplar-based image-to-image translation within deep convolutional neural networks (CNNs) generally require a training phase to optimize the network parameters on domain-specific and task-specific benchmarks, thus having limited applicability and generalization ability.

Image-to-Image Translation Translation

Exploiting Diffuse Multipath in 5G SLAM

no code implementations28 Jun 2020 Yu Ge, Hyowon Kim, Fuxi Wen, Lennart Svensson, Sunwoo Kim, Henk Wymeersch

5G millimeter wave (mmWave) signals can be used to jointly localize the receiver and map the propagation environment in vehicular networks, which is a typical simultaneous localization and mapping (SLAM) problem.

Simultaneous Localization and Mapping

Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation

1 code implementation14 Feb 2020 Sunwoo Kim, Haici Yang, Minje Kim

Speech enhancement tasks have seen significant improvements with the advance of deep learning technology, but with the cost of increased computational complexity.

Binary Classification Denoising +3

5G mmWave Cooperative Positioning and Mapping using Multi-Model PHD Filter and Map Fusion

1 code implementation26 Aug 2019 Hyowon Kim, Karl Granström, Lin Gao, Giorgio Battistelli, Sunwoo Kim, Henk Wymeersch

5G millimeter wave (mmWave) signals can enable accurate positioning in vehicular networks when the base station (BS) and vehicles are equipped with large antenna arrays.

Nearest Neighbor Search-Based Bitwise Source Separation Using Discriminant Winner-Take-All Hashing

no code implementations26 Aug 2019 Sunwoo Kim, Minje Kim

We propose an iteration-free source separation algorithm based on Winner-Take-All (WTA) hash codes, which is a faster, yet accurate alternative to a complex machine learning model for single-channel source separation in a resource-constrained environment.


Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation

no code implementations23 Aug 2019 Sunwoo Kim, Mrinmoy Maity, Minje Kim

Our experiments show that the proposed BGRU method produces source separation results greater than that of a real-valued fully connected network, with 11-12 dB mean Signal-to-Distortion Ratio (SDR).

Binarization Quantization

Cannot find the paper you are looking for? You can Submit a new open access paper.