22 citations · 67 across the 13 of their papers we have counts for
13 papers
InterHier: Learning Interconnected Hierarchical Semantics for Open-Vocabulary Object Detection
Yeong-Jin Kim, Ho-Joong Kim, Seong-Whan Lee
In this paper, we investigate the limitations of fixed, hand-crafted connectors in hierarchical semantic representations for open-vocabulary object detection. Existing methods esta…
Modularity-Free Conflict-Averse Training for Generalized PINNs
Heejo Kong, Beomchul Park, Sung-Jin Kim +1
Physics-informed neural networks (PINNs) have become a powerful framework for solving PDEs by embedding physical laws into differentiable objectives. Despite their advances, traini…
Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selection
Lintong Zhang, Kang Yin, Seong-Whan Lee
In the domain of non-generative visual counterfactual explanations (CE), traditional techniques frequently involve the substitution of sections within a query image with correspond…
ChemFixer: Correcting Invalid Molecules to Unlock Previously Unseen Chemical Space
Jun-Hyoung Park, Ho-Jun Song, Seong-Whan Lee
Deep learning-based molecular generation models have shown great potential in efficiently exploring vast chemical spaces by generating potential drug candidates with desired proper…
Consciousness-ECG Transformer for Conscious State Estimation System with Real-Time Monitoring
Young-Seok Kweon, Gi-Hwan Shin, Ji-Yong Kim +2
Conscious state estimation is important in various medical settings, including sleep staging and anesthesia management, to ensure patient safety and optimize health outcomes. Tradi…
Functional connectivity guided deep neural network for decoding high-level visual imagery
Byoung-Hee Kwon, Minji Lee, Seong-Whan Lee
This study introduces a pioneering approach in brain-computer interface (BCI) technology, featuring our novel concept of high-level visual imagery for non-invasive electroencephalo…
Diversify and Conquer: Open-set Disagreement for Robust Semi-supervised Learning with Outliers
Heejo Kong, Sung-Jin Kim, Gunho Jung +1
Conventional semi-supervised learning (SSL) ideally assumes that labeled and unlabeled data share an identical class distribution, however in practice, this assumption is easily vi…
Explaining generative diffusion models via visual analysis for interpretable decision-making process
Ji-Hoon Park, Yeong-Joon Ju, Seong-Whan Lee
Diffusion models have demonstrated remarkable performance in generation tasks. Nevertheless, explaining the diffusion process remains challenging due to it being a sequence of deno…
AM-SORT: Adaptable Motion Predictor with Historical Trajectory Embedding for Multi-Object Tracking
Vitaliy Kim, Gunho Jung, Seong-Whan Lee
Many multi-object tracking (MOT) approaches, which employ the Kalman Filter as a motion predictor, assume constant velocity and Gaussian-distributed filtering noises. These assumpt…
DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text Alignment
Hyung-Seok Oh, Sang-Hoon Lee, Deok-Hyeon Cho +1
Emotional voice conversion (EVC) involves modifying various acoustic characteristics, such as pitch and spectral envelope, to match a desired emotional state while preserving the s…
Improving Generalization of Drowsiness State Classification by Domain-Specific Normalization
Dong-Young Kim, Dong-Kyun Han, Seo-Hyeon Park +2
Abnormal driver states, particularly have been major concerns for road safety, emphasizing the importance of accurate drowsiness detection to prevent accidents. Electroencephalogra…
NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations
Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee
Despite deep learning (DL) has achieved remarkable progress in various domains, the DL models are still prone to making mistakes. This issue necessitates effective debugging tools…
DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training
Hyung-Seok Oh, Sang-Hoon Lee, Seong-Whan Lee
Expressive text-to-speech systems have undergone significant advancements owing to prosody modeling, but conventional methods can still be improved. Traditional approaches have rel…