ViTA

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.

Natural Language Processing4 results

Machine TranslationonHindi Visual Genome (Test Set)
BLEU (EN-HI)· uses extra data· 2021-06-01
44.6
SOTA
ViTA: Visual-Linguistic Translation by Aligning Object Tags arXiv:2106.00250
Machine TranslationonHindi Visual Genome (Challenge Set)
BLEU (EN-HI)· uses extra data· 2021-06-01
51.6
SOTA
ViTA: Visual-Linguistic Translation by Aligning Object Tags arXiv:2106.00250
Multimodal Machine TranslationonHindi Visual Genome (Test Set)
BLEU (EN-HI)· uses extra data· 2021-06-01
44.6
SOTA
ViTA: Visual-Linguistic Translation by Aligning Object Tags arXiv:2106.00250
Multimodal Machine TranslationonHindi Visual Genome (Challenge Set)
BLEU (EN-HI)· uses extra data· 2021-06-01
51.6
SOTA
ViTA: Visual-Linguistic Translation by Aligning Object Tags arXiv:2106.00250