Hyeonggon Ryu

multimodal learning (2) audio-visual learning (2) cross-modal retrieval (2) sound source localization (2) adversarial learning (1) semi-supervised learning (1) visual question answering (1) knowledge distillation (1) question answering (1) sound localization (1) bias mitigation (1) cross-modal alignment (1) classification model (1) multi-hop reasoning (1) cross-modal attention (1) semantic understanding (1) generative adversarial learning (1) ensemble debiasing (1) audio-visual grounding (1) audio comprehension (1)