KVL-BERTLARGE

Reported on 3 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 Processing3 results

Visual Question Answering (VQA)onVCR (Q-AR) test
Accuracy· 2020-12-13
60.3
best: 81.6 (GPT4RoI)
KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning arXiv:2012.07000
Visual Question Answering (VQA)onVCR (QA-R) test
Accuracy· 2020-12-13
78.6
best: 91 (GPT4RoI)
KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning arXiv:2012.07000
Visual Question Answering (VQA)onVCR (Q-A) test
Accuracy· 2020-12-13
76.4
best: 89.4 (GPT4RoI)
KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning arXiv:2012.07000