Video Question Answering On Sutd Trafficqa
Metriken
1/4
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | 1/4 |
|---|---|
| tem-adapter-adapting-image-text-pretraining | 46.0 |
| tvqa-localized-compositional-video-question | 35.16 |
| Modell 3 | 50.2 |
| hierarchical-conditional-relation-networks | 36.49 |
| trafficqa-a-question-answering-benchmark-and | 37.05 |
| exploring-models-and-data-for-image-question | 29.91 |