Visual Question Answering On Textvqa Test 1
Metriken
overall
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| PaLI | 73.1 | PaLI: A Jointly-Scaled Multilingual Language-Image Model |
| TAP | 53.97 | - |
| TAG | 53.69 | TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation |
| ssbaseline | 45.66 | - |
| SMA single model | 45.51 | - |
| SAM (Single Model) | 44.8 | - |
| colab_buaa | 44.73 | - |
| CRN (Single Model) | 40.96 | - |
| CIG | 40.77 | - |
| M4C | 40.46 | - |
| Shuai | 39.95 | - |
| mmgnn | 32.46 | - |
0 of 12 row(s) selected.