Vijay Mahadevan

attention mechanism (2) vision-language model (2) multimodal learning (2) knowledge distillation (2) transformer architecture (2) dimensionality reduction (2) encoder-decoder transformer (2) cross-modal retrieval (2) action recognition (1) background subtraction (1) feature learning (1) temporal dynamics (1) scene understanding (1) visual saliency (1) multi-task learning (1) feature extraction (1) named entity recognition (1) question answering (1) object tracking (1) manifold learning (1)