what model exactly for the features?

boheumd / A2Summ

The official implementation of 'Align and Attend: Multimodal Summarization with Dual Contrastive Losses' (CVPR 2023)

https://boheumd.github.io/A2Summ/

70 stars 10 forks source link

what model exactly for the features? #17

Open travisseng opened 7 months ago

travisseng commented 7 months ago

Hi, I wanted to know what version of CLIP you used and how did you get the features for Roberta ? Is it through average pooling or you took the features of the [CLS] token ?