53 citations
- Seoul National UniversityKR2 papers
- Yonsei UniversityKR2 papers
- Electronics and Telecommunications Research InstituteKR1 paper
- Gwangju Institute of Science and TechnologyKR1 paper
- Korea UniversityKR1 paper
- Sejong UniversityKR1 paper
- Seoul National University Bundang HospitalKR1 paper
- Soonchunhyang UniversityKR1 paper
- Sungkyunkwan UniversityKR1 paper
- University of EdinburghGB1 paper
12 papers
A Framework for Mining Collectively-Behaving Bots in MMORPGs
Hyunsoo Kim, Jun Hee Kim, Jaeman Son +2
In MMORPGs (Massively Multiplayer Online Role-Playing Games), abnormal players (bots) using unauthorized automated programs to carry out pre-defined behaviors systematically and re…
Bidirectional GaitNet: A Bidirectional Prediction Model of Human Gait and Anatomical Conditions
Jungnam Park, Moon Seok Park, Jehee Lee +1
We present a novel generative model, called Bidirectional GaitNet, that learns the relationship between human anatomy and its gait. The simulation model of human anatomy is a compr…
Varianceflow: High-Quality and Controllable Text-to-Speech using Variance Information via Normalizing Flow
Yoonhyung Lee, Jinhyeok Yang, Kyomin Jung
There are two types of methods for non-autoregressive text-to-speech models to learn the one-to-many relationship between text and speech effectively. The first one is to use an ad…
Hierarchical Context-Aware Transformers for Non-Autoregressive Text to Speech
Jae-Sung Bae, Tae-Jun Bak, Young-Sun Joo +1
In this paper, we propose methods for improving the modeling performance of a Transformer-based non-autoregressive text-to-speech (TNA-TTS) model. Although the text encoder and aud…
Self-Supervised Multimodal Opinion Summarization
Jinbae Im, Moonki Kim, Hoyeop Lee +2
Recently, opinion summarization, which is the generation of a summary from multiple reviews, has been conducted in a self-supervised manner by considering a sampled review as a pse…
CITIES: Contextual Inference of Tail-Item Embeddings for Sequential Recommendation
Seongwon Jang, Hoyeop Lee, Hyunsouk Cho +1
Sequential recommendation techniques provide users with product recommendations fitting their current preferences by handling dynamic user preferences over time. Previous studies h…