lennartmoritz
lennartmoritz
I've felt like in SEF the missions have become **way easier** than in the base game considering the amount of times you used to get blasted into oblivion by a...
If i read your paper right, you have frozen the CLIP text encoder and only aligned the other modalities. Do you think a pretrained [Long-CLIP](https://github.com/beichenzbc/Long-CLIP) model could be used as...
I am trying to verify/reproduce your paper's validation results **without training** it myself and expected 42.6% R@1 accuracy for MSR-VTT. But when I follow the instructions from [TRAIN_AND_VALIDATE.md](https://github.com/PKU-YuanGroup/LanguageBind/blob/main/TRAIN_AND_VALIDATE.md) (I only...