Arsha Nagrani

Core AI (1)

multimodal learning (16) video understanding (12) video captioning (5) contrastive learning (4) temporal localization (4) large language model (4) visual question answering (3) audio description (3) vision-language model (3) video question answering (3) self-supervised learning (3) automatic speech recognition (3) speaker verification (3) cross-modal learning (3) video-language model (3) dense video captioning (3) efficient computing (2) transformer architecture (2) zero-shot learning (2) semantic alignment (2)