Picture for Soo-Hyung Kim

Soo-Hyung Kim

Rethinking Top Probability from Multi-view for Distracted Driver Behaviour Localization

Add code
Nov 19, 2024
Viaarxiv icon

Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic Model

Add code
Oct 02, 2024
Viaarxiv icon

KAN-Based Fusion of Dual-Domain for Audio-Driven Facial Landmarks Generation

Add code
Sep 09, 2024
Viaarxiv icon

Leveraging WaveNet for Dynamic Listening Head Modeling from Speech

Add code
Sep 08, 2024
Figure 1 for Leveraging WaveNet for Dynamic Listening Head Modeling from Speech
Figure 2 for Leveraging WaveNet for Dynamic Listening Head Modeling from Speech
Figure 3 for Leveraging WaveNet for Dynamic Listening Head Modeling from Speech
Figure 4 for Leveraging WaveNet for Dynamic Listening Head Modeling from Speech
Viaarxiv icon

Transformer with Leveraged Masked Autoencoder for video-based Pain Assessment

Add code
Sep 08, 2024
Viaarxiv icon

Adaptation of Distinct Semantics for Uncertain Areas in Polyp Segmentation

Add code
May 13, 2024
Viaarxiv icon

DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in Conversation

Add code
Jul 31, 2023
Viaarxiv icon

Mental Workload Estimation with Electroencephalogram Signals by Combining Multi-Space Deep Models

Add code
Jul 23, 2023
Viaarxiv icon

Multi-scale Transformer-based Network for Emotion Recognition from Multi Physiological Signals

Add code
May 08, 2023
Viaarxiv icon

CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting

Add code
Mar 14, 2023
Viaarxiv icon