Soravit Changpinyo

visual question answering (12) image captioning (8) multimodal learning (6) object detection (5) vision language (2) transfer learning (2) vision language model (2) long-tailed distribution (2) faster r-cnn (2) zero-shot learning (2) manifold learning (1) model calibration (1) domain generalization (1) text-to-image synthesis (1) metric learning (1) similarity learning (1) video understanding (1) image retrieval (1) few-shot learning (1) expectation maximization (1)