A new video-text dataset which may help

[mutonix]

Vript is a fine-grained video-text dataset with 12K annotated high-resolution videos (~400k clips), where each clip has a detailed caption of ~145 words.

[chg0901]

Could you please propose a pr in the dataset section?

[TruthSearcher]

Vript is a fine-grained video-text dataset with 12K annotated high-resolution videos (~400k clips), where each clip has a detailed caption of ~145 words.

isn't that a non-commercial dataset?

[mutonix]

It is non-commercial and academic only.

[chg0901]

Could you please propose a pr in the dataset section?

@mutonix