Xiangteng He

cross-modal retrieval (2) deep reinforcement learning (1) multi-modal learning (1) benchmark evaluation (1) metric learning (1) few-shot learning (1) action recognition (1) image generation (1) anomaly detection (1) attention mechanism (1) model evaluation (1) multimodal learning (1) cross-modal learning (1) incremental learning (1) representation learning (1) video understanding (1) image editing (1) visual representation (1) temporal grounding (1) unsupervised learning (1)