Visual Question Answering On Vcr Qa R Dev
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Accuracy | Paper Title | Repository |
|---|---|---|---|
| VL-BERTBASE | 74.4 | VL-BERT: Pre-training of Generic Visual-Linguistic Representations | |
| VL-BERTLARGE | 77.9 | VL-BERT: Pre-training of Generic Visual-Linguistic Representations | |
| VisualBERT | 73.2 | VisualBERT: A Simple and Performant Baseline for Vision and Language |
0 of 3 row(s) selected.