Alibaba-VELLDEPTH
/

CTVG-4B

Video-Text-to-Text

image-text-to-text

video-temporal-grounding

temporal-localization

confidence-estimation

Model card Files Files and versions

CTVG-4B / README.md

Commit History

Oct 10 24 days ago

07:07
Link CTVG-4B model card to the public GitHub code repository

DexterChan

Verified signature
a6e2a5a
06:19
Upload CTVG-4B with matched confidence head and model card

DexterChan

Verified signature
ad3d8ed
04:28
initial commit

DexterChan

Verified signature
288c367