KOR ENG

연구 성과

2026. 03. 24

Transformer-based Unified Recognition of Two Hands Manipulating Objects (CVPR 2023), Prof. Seungryul Baek

Transformer-Based Unified Recognition of Two Hands Manipulating Objects CVPR 2023  ·  Hoseong Cho, Chanwoo Kim, Jihyeon Kim, Seongyeong Lee, Elkhan Ismayilzada, Seungryul Baek ·  Edit social preview Understanding the hand-object interactions from an egocentric video has received a great attention recently. So far, most approaches are based on the convolutional neural network (CNN) features combined with...

2026. 03. 24

BoIR: Box-Supervised Instance Representation for Multi Person Pose Estimation (BMVC 2023), Prof. Seungryul Baek

BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation Uyoung Jeong, Seungryul Baek, Hyung Jin Chang, Kwang In Kim Single-stage multi-person human pose estimation (MPPE) methods have shown great performance improvements, but existing methods fail to disentangle features by individual instances under crowded scenes. In this paper, we propose a bounding...

2026. 03. 24

CONVERSATION CHRONICLES: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations (EMNLP 2023), Prof. Hyounghun Kim

Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations Jihyoung Jang, Minseong Boo, Hyounghun Kim Abstract In the field of natural language processing, open-domain chatbots have emerged as an important research topic. However, a major limitation of existing open-domain chatbot research is its singular focus on short single-session...

2026. 03. 24

Generating Realistic Images from In-the-wild Sounds (ICCV 2023), Prof. Taehwan Kim

Generating Realistic Images from In-the-wild Sounds Taegyeong Lee, Jeonghun Kang, Hyeonyu Kim, Taehwan Kim Representing wild sounds as images is an important but challenging task due to the lack of paired datasets between sound and images and the significant differences in the characteristics of these two modalities. Previous studies have...

2026. 03. 24

Heavy-tailed linear bandit with Huber regression (UAI 2023), Prof. Gi-Soo Kim

Heavy-tailed linear bandit with huber regression Authors: Minhyun Kang, Gi-Soo Kim ABSTRACT Linear bandit algorithms have been extensively studied and have shown successful in sequential decision tasks despite their simplicity. Many algorithms however work under the assumption that the reward is the sum of linear function...

2026. 03. 24

MMP Net: A feedforward neural network model with sequential inputs for representing continuous multistage manufacturing processes without intermediate outputs (IISE Trans.), Prof. Chiehyeon Lim

MMP Net: A Feedforward Neural Network Model with Sequential Inputs for Representing Continuous Multistage Manufacturing Processes without Intermediate Outputs IISE Transactions ( IF 2.6 ) Pub Date: 2023-07-28 , DOI:10.1080/24725854.2023.2242434 Cho Hojin, Kim Kyeongbin, Yoon Kihyuk, Chun Jaewook, Kim Jaeyong, Lee Kyeongmin, Lee Junghye, Chiehyeon Lim Abstract Machine learning models that are used for the prediction and...