Jinze Li

cross-modal alignment (2) object detection (1) multimodal recommendation (1) collaborative filtering (1) self-supervised learning (1) multimodal learning (1) multi-modal learning (1) feature interaction (1) loss function (1) multiple clustering (1) intersection over union (1) visual modality (1) bounding box regression (1) long-horizon task (1) graph neural network (1) non-maximum suppression (1) interaction information (1) agent memory (1) proxy learning (1) distance loss (1)