Phrase Grounding On Referit
Metrics
Pointing Game Accuracy
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| VG_BiLSTM_VGG | 62.76 | Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding |
| GbS Ensemble MS-COCO | 58.21 | Detector-Free Weakly Supervised Grounding by Separation |
| MCB | - | Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding |
0 of 3 row(s) selected.