paper-with-me

Visual Question Answering (VQA) 벤치마크

Visual Question Answering (VQA) on VCR (Q-A) dev

3개 결과 · ⬇ CSV · JSON

Accuracy

70.8 71.97 73.15 74.33 75.5 2019-08 2026-09 VisualBERT — 70.8 (2019-08-09) VL-BERTLARGE — 75.5 (2019-08-22) VL-BERTBASE — 73.8 (2019-08-22) VisualBERT — 70.8 (2019-08-09) VL-BERTLARGE — 75.5 (2019-08-22)
RankModel Accuracy PaperCodeYear
1 VL-BERTLARGE 75.5 VL-BERT: Pre-training of Generic Visual-Linguistic Representations jackroos/VL-BERT · ImperialNLP/BertGen · jules-samaran/vl-bert 2019
2 VL-BERTBASE 73.8 VL-BERT: Pre-training of Generic Visual-Linguistic Representations jackroos/VL-BERT · ImperialNLP/BertGen · jules-samaran/vl-bert 2019
3 VisualBERT 70.8 VisualBERT: A Simple and Performant Baseline for Vision and Language uclanlp/visualbert · YIKUAN8/Transformers-VQA · lalithjets/surgical_vqa · +7 2019
1–3 / 3 페이지당 10 20 50 100