search

antoyang / FrozenBiLM

[NeurIPS 2022] Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
https://arxiv.org/abs/2206.08155
Apache License 2.0
153 stars 23 forks source link

Few-shot VideoQA training details #9

Closed engindeniz closed 1 year ago

engindeniz commented 1 year ago

Hi,

Thanks for the great work and publicly available code.

Could you please share the few-shot training parameters (batch size, learning rate, etc.)? I could not reproduce the results.

Thanks in advance.

antoyang commented 1 year ago

Hi, Thanks for your interest! For the few-shot setting, I ran the same hyperparameter swipes as for the fully-supervised setting (see Section 4.1 and Appendix Section C.2).