Pengwan Yang

few-shot learning (2) transformer architecture (1) representation learning (1) contrastive learning (1) continual learning (1) catastrophic forgetting (1) semantic segmentation (1) self-supervised learning (1) attention mechanism (1) point cloud (1) 3d vision (1) video understanding (1) action localization (1) spatio-temporal localization (1) low-rank adaptation (1) multimodal large language model (1) parameter efficiency (1) encoder-decoder structure (1) multi-scale context (1) one-shot learning (1)