Angie Boggust

video retrieval (3) self-supervised learning (3) multimodal learning (2) instructional video (2) cross-lingual transfer (1) text generation (1) semantic analysis (1) audio-visual learning (1) scene graph (1) language model (1) feature sensitivity (1) attention map (1) multilingual learning (1) multilingual representation (1) cross-lingual retrieval (1) zero-shot retrieval (1) grounded language (1) multimodal clustering (1) vision transformer explainability (1) gradient-based explanation (1)