Vijay Kumar B G

open-vocabulary object detection (2) large language model (2) object detection (2) open-vocabulary detection (2) style transfer (1) embedding learning (1) video generation (1) visual question answering (1) data augmentation (1) question decomposition (1) referring expression (1) visual reasoning (1) pseudo labeling (1) generative model (1) diffusion model (1) convolutional neural network (1) tool use (1) model generalization (1) text-to-image diffusion (1) private learning (1)