ORG-TRL

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 CaptioningonVATEX
BLEU-4· uses extra data· 2020-02-26
32.1
best: 45.6 (VALOR)
SOTA
Object Relational Graph with Teacher-Recommended Learning for Video Captioning arXiv:2002.11566
Video CaptioningonVATEX
CIDEr· uses extra data· 2020-02-26
49.7
best: 99.5 (VAST)
SOTA
Object Relational Graph with Teacher-Recommended Learning for Video Captioning arXiv:2002.11566
Video CaptioningonVATEX
METEOR· uses extra data· 2020-02-26
22.2
best: 29.4 (VALOR)
SOTA
Object Relational Graph with Teacher-Recommended Learning for Video Captioning arXiv:2002.11566
Video CaptioningonVATEX
ROUGE-L· uses extra data· 2020-02-26
48.9
best: 57.4 (VALOR)
SOTA
Object Relational Graph with Teacher-Recommended Learning for Video Captioning arXiv:2002.11566