VLCap (ae-test split) - Appearance + Language

Reported on 4 benchmarks across 1 task · 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 CaptioningonActivityNet Captions
BLEU4· 2022-06-26
13.38
best: 14.7 (VideoCoCa)
SOTA
VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning arXiv:2206.12972
Video CaptioningonActivityNet Captions
CIDEr· 2022-06-26
31.29
best: 39.3 (VideoCoCa)
SOTA
VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning arXiv:2206.12972
Video CaptioningonActivityNet Captions
METEOR· 2022-06-26
17.48
best: 17.97 (VLTinT (ae-test split) C3D/Ling)
SOTA
VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning arXiv:2206.12972
Video CaptioningonActivityNet Captions
ROUGE-L· 2022-06-26
35.99
best: 36.56 (VLTinT (ae-test split) C3D/Ling)
SOTA
VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning arXiv:2206.12972