All of Moments Lab Research papers available on Hugging Face
-
Towards Retrieval Augmented Generation over Large Video Libraries
Paper • 2406.14938 • Published • 22 -
Inserting Faces inside Captions: Image Captioning with Attention Guided Merging
Paper • 2405.02305 • Published • 2 -
Multimodal Chaptering for Long-Form TV Newscast Video
Paper • 2406.17590 • Published • 2 -
PEEK: Picking Essential frames via Efficient Knowledge distillation
Paper • 2605.31029 • Published • 20