Jilan Xu

video understanding (4) multimodal learning (2) semantic segmentation (2) action detection (2) video segmentation (1) open-vocabulary detection (1) benchmark evaluation (1) multimodal dataset (1) vision transformer (1) egocentric vision (1) multi-modal learning (1) in-context learning (1) video instance segmentation (1) medical image segmentation (1) human motion (1) multitask learning (1) temporal analysis (1) gaussian mixture model (1) video captioning (1) semi-supervised learning (1)