Mohammadreza Salehi

self-supervised learning (3) vision-language model (2) multimodal learning (2) transformer architecture (2) video understanding (2) multi-task learning (1) visual question answering (1) zero-shot learning (1) anomaly detection (1) transfer learning (1) contrastive learning (1) optimal transport (1) action recognition (1) attention mechanism (1) text editing (1) knowledge transfer (1) knowledge distillation (1) text generation (1) few-shot learning (1) representation learning (1)