Hyeran Byun

semantic segmentation (3) temporal action localization (3) contrastive learning (3) domain adaptation (3) weakly supervised learning (3) style transfer (3) action recognition (2) representation learning (2) facial attribute classification (2) generative adversarial network (2) attention mechanism (2) video understanding (2) weakly-supervised learning (2) self-supervised learning (1) video classification (1) feature extraction (1) vision transformer (1) image synthesis (1) uncertainty modeling (1) supervised learning (1)