Huiyu Wang

video understanding (4) semantic segmentation (4) masked autoencoder (4) zero-shot learning (3) egocentric video (3) multimodal learning (3) mask transformer (2) panoptic segmentation (2) procedural activity (2) self-supervised learning (2) convolutional neural network (2) instance segmentation (2) egocentric vision (2) activity recognition (2) video question answering (2) video segmentation (2) vision transformer (2) pose estimation (1) anomaly detection (1) domain adaptation (1)