Yicong Li

multimodal learning (6) video question answering (6) cross-modal interaction (3) video understanding (3) graph neural network (3) temporal grounding (2) self-supervised learning (2) visual question answering (2) affordance segmentation (2) domain generalization (2) visual grounding (2) vision-language model (2) egocentric vision (2) temporal reasoning (1) vision transformer (1) link prediction (1) 3d reconstruction (1) hierarchical learning (1) temporal dynamics (1) semantic segmentation (1)