Guoxin Xiong

few-shot learning (3) prototype learning (2) semantic segmentation (2) point cloud segmentation (2) optimal transport (1) multi-modal learning (1) temporal alignment (1) temporal consistency (1) video-text retrieval (1) few-shot semantic segmentation (1) noisy correspondence (1) mutual aggregation (1) semantic inconsistency (1) support sample (1) video object segmentation (1) large language model (1) few-shot video object segmentation (1) part feature learning (1) support-query alignment (1) representation learning (1)