7.5k citations · 7.6k across the 15 of their papers we have counts for
15 papers
Gated Low-rank Adaptation for personalized Code-Switching Automatic Speech Recognition on the low-spec devices
Gwantae Kim, Bokyeung Lee, Donghyeon Kim +1
In recent times, there has been a growing interest in utilizing personalized large models on low-spec devices, such as mobile and CPU-only devices. However, utilizing a personalize…
Two-stream Decoder Feature Normality Estimating Network for Industrial Anomaly Detection
Chaewon Park, Minhyeok Lee, Suhwan Cho +2
Image reconstruction-based anomaly detection has recently been in the spotlight because of the difficulty of constructing anomaly datasets. These approaches work by learning to mod…
Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
Suhwan Cho, Minhyeok Lee, Seunghoon Lee +3
Unsupervised video object segmentation (VOS) aims to detect the most salient object in a video sequence at the pixel level. In unsupervised VOS, most state-of-the-art methods lever…
FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detection
Donghyeong Kim, Chaewon Park, Suhwan Cho +1
Feature embedding-based methods have shown exceptional performance in detecting industrial anomalies by comparing features of target images with normal images. However, some method…
Discriminatory and orthogonal feature learning for noise robust keyword spotting
Donghyeon Kim, Kyungdeuk Ko, David K. Han +1
Keyword Spotting (KWS) is an essential component in a smart device for alerting the system when a user prompts it with a command. As these devices are typically constrained by comp…
Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis
Jeong-gi Kwak, Yuanming Li, Dongsik Yoon +3
Over the years, 2D GANs have achieved great successes in photorealistic portrait generation. However, they lack 3D understanding in the generation process, thus they suffer from mu…
Efficient dynamic filter for robust and low computational feature extraction
Donghyeon Kim, Gwantae Kim, Bokyeung Lee +3
Unseen noise signal which is not considered in a model training process is difficult to anticipate and would lead to performance degradation. Various methods have been investigated…
BERN2: an advanced neural biomedical named entity recognition and normalization tool
Mujeen Sung, Minbyul Jeong, Yonghwa Choi +3
In biomedical natural language processing, named entity recognition (NER) and named entity normalization (NEN) are key tasks that enable the automatic extraction of biomedical enti…
Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN
Jeong-gi Kwak, Youngsaeng Jin, Yuanming Li +3
Adverse weather image translation belongs to the unsupervised image-to-image (I2I) translation task which aims to transfer adverse condition domain (eg, rainy night) to standard do…
A Lightweight dynamic filter for keyword spotting
Donghyeon Kim, Kyungdeuk Ko, Jeonggi Kwak +2
Keyword Spotting (KWS) from speech signals is widely applied to perform fully hands-free speech recognition. The KWS network is designed as a small-footprint model so it can contin…
Transferability of Natural Language Inference to Biomedical Question Answering
Minbyul Jeong, Mujeen Sung, Gangwoo Kim +4
Biomedical question answering (QA) is a challenging task due to the scarcity of data and the requirement of domain expertise. Pre-trained language models have been used to address…
Building a PubMed knowledge graph
Jian Xu, Sunkyu Kim, Min Song +12
PubMed is an essential resource for the medical domain, but useful concepts are either difficult to extract or are ambiguated, which has significantly hindered knowledge discovery.…
Pre-trained Language Model for Biomedical Question Answering
Wonjin Yoon, Jinhyuk Lee, Donghyeon Kim +2
The recent success of question answering systems is largely attributed to pre-trained language models. However, as language models are mostly pre-trained on general domain corpora…
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Jinhyuk Lee, Wonjin Yoon, Sungdong Kim +4
Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows. With the progress in natural language processing (NLP), extracting va…
Learning User Preferences and Understanding Calendar Contexts for Event Scheduling
Donghyeon Kim, Jinhyuk Lee, Donghee Choi +2
With online calendar services gaining popularity worldwide, calendar data has become one of the richest context sources for understanding human behavior. However, event scheduling…