Sunok Kim

Shape-robust SAR ship detection via context-preserving augmentation and deep contrastive roi learning

Context-preserving instance-level augmentation and deformable convolution networks for SAR ship detection

Stereo confidence estimation via locally adaptive fusion and knowledge distillation

Meta-confidence estimation for stereo matching

Looking into your speech: Learning cross-modal affinity for audio-visual speech separation

On the confidence of stereo matching in a deep-learning era: a quantitative evaluation

Adaptive confidence thresholding for monocular depth estimation

Multi-modal recurrent attention networks for facial expression recognition