Yunzhi Zhuge

semantic segmentation (3) vision-language model (2) contrastive learning (2) saliency detection (2) continual learning (2) mixture of expert (2) salient object detection (2) multimodal large language model (2) multi-task learning (1) multimodal learning (1) image segmentation (1) feature embedding (1) monocular depth estimation (1) multi-modal learning (1) temporal reasoning (1) weak supervision (1) video segmentation (1) object tracking (1) video instance segmentation (1) scene understanding (1)