Xudong Lin

multimodal learning (15) video understanding (7) zero-shot learning (4) event extraction (4) video question answering (3) contrastive learning (3) video grounding (3) few-shot learning (3) video captioning (3) semantic alignment (2) video retrieval (2) event coreference (2) visual grounding (2) coreference resolution (2) transfer learning (2) unsupervised learning (2) visual question answering (2) weakly supervised learning (2) vision transformer (2) self-supervised learning (2)