Search Results for author: Hanseok Ko

Found 19 papers, 6 papers with code

Generate and Edit Your Own Character in a Canonical View

no code implementations6 May 2022 Jeong-gi Kwak, Yuanming Li, Dongsik Yoon, David Han, Hanseok Ko

Although the progress of generative models enables the stylization of a portrait, obtaining the stylized image in canonical view is still a challenging task.

Efficient dynamic filter for robust and low computational feature extraction

no code implementations3 May 2022 Donghyeon Kim, Gwantae Kim, Bokyeung Lee, Jeong-gi Kwak, David K. Han, Hanseok Ko

However, the performance of the dynamic filter might be degraded since simple feature pooling is used to reduce the computational resource in the IDF part.

Keyword Spotting Speaker Verification

Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN

1 code implementation8 Dec 2021 Jeong-gi Kwak, Youngsaeng Jin, Yuanming Li, Dongsik Yoon, Donghyeon Kim, Hanseok Ko

To address this issue, we propose a novel GAN model, i. e., AU-GAN, which has an asymmetric architecture for adverse domain translation.

Disentanglement Translation

Action Recognition with Domain Invariant Features of Skeleton Image

no code implementations19 Nov 2021 Han Chen, Yifan Jiang, Hanseok Ko

Due to the fast processing-speed and robustness it can achieve, skeleton-based action recognition has recently received the attention of the computer vision community.

Action Recognition Skeleton Based Action Recognition

A Teacher-Student Framework with Fourier Augmentation for COVID-19 Infection Segmentation in CT Images

no code implementations13 Oct 2021 Han Chen, Yifan Jiang, Hanseok Ko, Murray Loew

Automatic segmentation of infected regions in computed tomography (CT) images is necessary for the initial diagnosis of COVID-19.

Computed Tomography (CT)

Lightweight dynamic filter for keyword spotting

no code implementations23 Sep 2021 Donghyeon Kim, Kyungdeuk Ko, Jeong-gi Kwak, David K. Han, Hanseok Ko

This lightweight dynamic filter is applied to the front-end of KWS to enhance the separability of the input data.

Keyword Spotting Speech Recognition

Memory-based Semantic Segmentation for Off-road Unstructured Natural Environments

1 code implementation12 Aug 2021 Youngsaeng Jin, David K. Han, Hanseok Ko

In this paper, a built-in memory module for semantic segmentation is proposed to overcome these problems.

Autonomous Driving Semantic Segmentation

CPNet: Cross-Parallel Network for Efficient Anomaly Detection

no code implementations10 Aug 2021 Youngsaeng Jin, Jonghwan Hong, David Han, Hanseok Ko

Anomaly detection in video streams is a challenging problem because of the scarcity of abnormal events and the difficulty of accurately annotating them.

Anomaly Detection Frame

Few-shot Learning for CT Scan based COVID-19 Diagnosis

no code implementations1 Feb 2021 Yifan Jiang, Han Chen, David K. Han, Hanseok Ko

To compensate for the sparseness of labeled data, the proposed method utilizes a large amount of synthetic COVID-19 CT images and adjusts the networks from the source domain (synthetic data) to the target domain (real data) with a cross-domain training mechanism.

Computed Tomography (CT) COVID-19 Diagnosis +2

CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature

1 code implementation ECCV 2020 Jeong-gi Kwak, David K. Han, Hanseok Ko

The goal of face attribute editing is altering a facial image according to given target attributes such as hair color, mustache, gender, etc.

Unsupervised domain adaptation based COVID-19 CT infection segmentation network

no code implementations23 Nov 2020 Han Chen, Yifan Jiang, Murray Loew, Hanseok Ko

In this paper, we propose an unsupervised domain adaptation based segmentation network to improve the segmentation performance of the infection areas in COVID-19 CT images.

Computed Tomography (CT) Unsupervised Domain Adaptation

COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network

no code implementations29 Jul 2020 Yifan Jiang, Han Chen, Murray Loew, Hanseok Ko

However, training a deep-learning model requires large volumes of data, and medical staff faces a high risk when collecting COVID-19 CT data due to the high infectivity of the disease.

Computed Tomography (CT) COVID-19 Diagnosis +2

Data Separability for Neural Network Classifiers and the Development of a Separability Index

1 code implementation27 May 2020 Shuyue Guan, Murray Loew, Hanseok Ko

In machine learning, the performance of a classifier depends on both the classifier model and the dataset.

Correlation Distance Skip Connection Denoising Autoencoder (CDSK-DAE) for Speech Feature Enhancement

no code implementations26 Jul 2019 Alzahra Badi, Sangwook Park, David K. Han, Hanseok Ko

Performance of learning based Automatic Speech Recognition (ASR) is susceptible to noise, especially when it is introduced in the testing data while not presented in the training data.

Automatic Speech Recognition Denoising +1

KU-ISPL Speaker Recognition Systems under Language mismatch condition for NIST 2016 Speaker Recognition Evaluation

no code implementations3 Feb 2017 Suwon Shon, Hanseok Ko

As development dataset which is spoken in Cebuano and Mandarin, we could prepare the evaluation trials through preliminary experiments to compensate the language mismatched condition.

Speaker Recognition

KU-ISPL Language Recognition System for NIST 2015 i-Vector Machine Learning Challenge

no code implementations21 Sep 2016 Suwon Shon, Seongkyu Mun, John H. L. Hansen, Hanseok Ko

The experimental results show that the use of duration and score fusion improves language recognition performance by 5% relative in LRiMLC15 cost.

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