Visual Question Answering On Msvd Qa 2
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Just Ask | 0.463 | Just Ask: Learning to Answer Questions from Millions of Narrated Videos | |
| FrozenBiLM | 0.548 | Zero-Shot Video Question Answering via Frozen Bidirectional Language Models |
0 of 2 row(s) selected.