Hamid Rezatofighi

trajectory prediction (3) object detection (3) domain adaptation (3) representation learning (2) social robot (2) large language model (2) generative adversarial network (2) visual reasoning (2) multi-object tracking (2) loss function (2) graph attention network (2) intersection over union (2) self-supervised learning (2) pose tracking (2) video understanding (2) object tracking (2) human pose estimation (2) vision-language model (2) robot perception (1) semantic segmentation (1)