MDETR-ENB5

Reported on 4 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Natural Language Processing4 results

Phrase GroundingonFlickr30k Entities Test
R@1· uses extra data· 2021-04-26
84.3
best: 87.7 (GLIPv2)
SOTA
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding arXiv:2104.12763
Phrase GroundingonFlickr30k Entities Test
R@10· uses extra data· 2021-04-26
95.8
best: 98.1 (GLIP)
SOTA
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding arXiv:2104.12763
Phrase GroundingonFlickr30k Entities Test
R@5· uses extra data· 2021-04-26
93.9
best: 96.9 (GLIP)
SOTA
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding arXiv:2104.12763
Visual Question Answering (VQA)onGQA test-std
Accuracy· 2021-04-26
62.45
best: 65.14 (ProTo)
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding arXiv:2104.12763