Mingqian Feng

image classification (1) benchmark evaluation (1) domain generalization (1) video captioning (1) multimodal learning (1) bias detection (1) video understanding (1) object tracking (1) empirical evaluation (1) bias mitigation (1) vision language model (1) multimodal large language model (1) multimodal language model (1) cross-modal embedding (1) clip embedding (1) temporal coherence (1) video question answering (1) partial least square (1) subgroup discovery (1) model fairness (1)