E2ESG

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Computer Vision4 results

Video CaptioningonViTT
CIDEr· uses extra data· 2022-04-18
25
best: 51.2 (HiCM²)
SOTA
End-to-end Dense Video Captioning as Sequence Generation arXiv:2204.08121
Video CaptioningonViTT
METEOR· uses extra data· 2022-04-18
8.1
best: 9.6 (HiCM²)
SOTA
End-to-end Dense Video Captioning as Sequence Generation arXiv:2204.08121
Dense Video CaptioningonViTT
CIDEr· uses extra data· 2022-04-18
25
best: 51.2 (HiCM²)
SOTA
End-to-end Dense Video Captioning as Sequence Generation arXiv:2204.08121
Dense Video CaptioningonViTT
METEOR· uses extra data· 2022-04-18
8.1
best: 9.6 (HiCM²)
SOTA
End-to-end Dense Video Captioning as Sequence Generation arXiv:2204.08121