Agrim Gupta

multimodal learning (3) generative adversarial network (2) semantic segmentation (2) video understanding (2) object detection (1) video captioning (1) benchmark evaluation (1) scene graph (1) imitation learning (1) prompt-based learning (1) trajectory prediction (1) image synthesis (1) egocentric vision (1) prompt engineering (1) text-to-image generation (1) visual reasoning (1) object tracking (1) instance segmentation (1) self-supervised learning (1) image generation (1)