Tags

13 unique topics
#data-centric (4) #dense video captioning (4) #zero-shot captioning (2) #driver monitoring (1) #fine-tuning (1) #grapheme-to-phoneme (1) #multilingual speech (1) #retrieval-augmented generation (1) #safety (1) #text-video retrieval (1) #video qa (1) #vision-language (1) #vision-language model (1)