B-Ultra

Reported on 5 benchmarks across 1 task · 1 paper · 1 SOTA

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

Natural Language Processing5 results

Visual Question Answering (VQA)onVizWiz 2018
number· 2019-09-04
28.81
SOTA
Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering arXiv:1909.02097
Visual Question Answering (VQA)onVizWiz 2018
other· 2019-09-04
35.41
best: 39 (LXR955, No Ensemble)
Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering arXiv:1909.02097
Visual Question Answering (VQA)onVizWiz 2018
overall· 2019-09-04
53.68
best: 55.4 (LXR955, No Ensemble)
Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering arXiv:1909.02097
Visual Question Answering (VQA)onVizWiz 2018
unanswerable· 2019-09-04
84.03
best: 80.48 (DVW)
Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering arXiv:1909.02097
Visual Question Answering (VQA)onVizWiz 2018
yes/no· 2019-09-04
68.12
best: 74 (LXR955, No Ensemble)
Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering arXiv:1909.02097