COOT (ae-test split) - Only Appearance features

Reported on 5 benchmarks across 1 task · 1 paper · 5 SOTA

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

Computer Vision5 results

Video CaptioningonActivityNet Captions
BLEU-3· 2020-11-01
17.43
SOTA
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning arXiv:2011.00597
Video CaptioningonActivityNet Captions
BLEU4· 2020-11-01
10.85
best: 14.7 (VideoCoCa)
SOTA
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning arXiv:2011.00597
Video CaptioningonActivityNet Captions
CIDEr· 2020-11-01
28.19
best: 39.3 (VideoCoCa)
SOTA
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning arXiv:2011.00597
Video CaptioningonActivityNet Captions
METEOR· 2020-11-01
15.99
best: 17.97 (VLTinT (ae-test split) C3D/Ling)
SOTA
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning arXiv:2011.00597
Video CaptioningonActivityNet Captions
ROUGE-L· 2020-11-01
31.45
best: 36.56 (VLTinT (ae-test split) C3D/Ling)
SOTA
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning arXiv:2011.00597