Intent Classification on English Text+Image Intent Dataset
0.794AccuracyCross-Modal Alignment
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Cross-Modal AlignmentLanguage=English, Modality=Text+Image, Fusion Strategy=Graph Networks2025.11 | 0.794 | 0.789 |
| Method | Links | ||
|---|---|---|---|
| Cross-Modal AlignmentLanguage=English, Modality=Text+Image, Fusion Strategy=Graph Networks2025.11 | 0.794 | 0.789 |