Image-to-Text Retrieval on Stock 10K (test)
36.98R@1Multimodal Contrastive Training
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Multimodal Contrastive TrainingBackbone=Frozen visual backbone2021.04 | 36.98 | 74.02 | 2 | |
| Stock-supTraining=Supervised on tagging task2021.04 | 33.76 | 71.22 | 3 |