MSR + MS Cog. Svcs.

Reported on 4 benchmarks across 1 task · 1 paper

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

Natural Language Processing4 results

Visual Question Answering (VQA)onVQA v2 test-std
number· 2021-01-02
61.5
best: 72.24 (ONE-PEACE)
VinVL: Revisiting Visual Representations in Vision-Language Models arXiv:2101.00529
Visual Question Answering (VQA)onVQA v2 test-std
other· 2021-01-02
66.68
best: 77.02 (mPLUG-Huge)
VinVL: Revisiting Visual Representations in Vision-Language Models arXiv:2101.00529
Visual Question Answering (VQA)onVQA v2 test-std
overall· 2021-01-02
76.63
best: 84.03 (BEiT-3)
VinVL: Revisiting Visual Representations in Vision-Language Models arXiv:2101.00529
Visual Question Answering (VQA)onVQA v2 test-std
yes/no· 2021-01-02
92.04
best: 94.85 (ONE-PEACE)
VinVL: Revisiting Visual Representations in Vision-Language Models arXiv:2101.00529