Qimei Cui

contrastive learning (2) representation learning (1) benchmark evaluation (1) anomaly detection (1) image retrieval (1) multimodal learning (1) video understanding (1) video anomaly detection (1) robust learning (1) vision language model (1) cross-modal alignment (1) node classification (1) image-text alignment (1) prompt-based method (1) graph convolution network (1) out-of-distribution robustness (1) heterophilic graph (1) multimodal sarcasm detection (1) text-image pair (1) large language model (1)