VLTinT (ae-test split) C3D/Ling

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 CaptioningonActivityNet Captions
BLEU4· 2022-11-28
14.5
best: 14.7 (VideoCoCa)
SOTA
VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning arXiv:2211.15103
Video CaptioningonActivityNet Captions
METEOR· 2022-11-28
17.97
SOTA
VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning arXiv:2211.15103
Video CaptioningonActivityNet Captions
ROUGE-L· 2022-11-28
36.56
SOTA
VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning arXiv:2211.15103
Video CaptioningonActivityNet Captions
CIDEr· 2022-11-28
31.13
best: 39.3 (VideoCoCa)
VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning arXiv:2211.15103