Pith. sign in

Video recap: Recursive captioning of hour-long videos

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Extending Video Masked Autoencoders to 128 frames

cs.CV · 2024-11-20 · conditional · novelty 6.0

A frozen token-importance scorer trained with an FSQ-MagViT tokenizer enables 128-frame masked-autoencoder pre-training, which outperforms 32-frame pre-training and sets state-of-the-art results on Diving48 and EPIC-Kitchens-100 verbs.

citing papers explorer

Showing 1 of 1 citing paper.

  • Extending Video Masked Autoencoders to 128 frames cs.CV · 2024-11-20 · conditional · none · ref 8

    A frozen token-importance scorer trained with an FSQ-MagViT tokenizer enables 128-frame masked-autoencoder pre-training, which outperforms 32-frame pre-training and sets state-of-the-art results on Diving48 and EPIC-Kitchens-100 verbs.