MV-GPT

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Video CaptioningonMSR-VTT
BLEU-4· uses extra data· 2022-01-20
48.9
best: 57.8 (mPLUG-2)
SOTA
End-to-end Generative Pretraining for Multimodal Video Captioning arXiv:2201.08264
Video CaptioningonMSR-VTT
CIDEr· uses extra data· 2022-01-20
60
best: 80 (mPLUG-2)
SOTA
End-to-end Generative Pretraining for Multimodal Video Captioning arXiv:2201.08264
Video CaptioningonMSR-VTT
METEOR· uses extra data· 2022-01-20
38.7
SOTA
End-to-end Generative Pretraining for Multimodal Video Captioning arXiv:2201.08264
Video CaptioningonMSR-VTT
ROUGE-L· uses extra data· 2022-01-20
64
best: 70.1 (mPLUG-2)
End-to-end Generative Pretraining for Multimodal Video Captioning arXiv:2201.08264