Phrase Localization on VisualGenome (test)
62.31Pointing AccuracyWWbL
Evaluation Results
| Method | Links | |
|---|---|---|
| WWbLBackbone=CLIP+VGG, Training source=VG2022.06 | 62.31 | |
| WWbLBackbone=CLIP+VGG, Training source=MS COCO2022.06 | 59.09 | |
| ELMo+PNASNetTraining=VG2018.11 | 55.16 | |
| GAEBackbone=CLIP, Training source=VG2022.06 | 54.72 | |
| GAEBackbone=CLIP, Training source=MS COCO2022.06 | 54.72 | |
| GbSBackbone=VGG, Training source=VG2022.06 | 53.4 | |
| ELMo+PNASNetTraining=MSCOCO2018.11 | 52.33 | |
| GbSBackbone=VGG, Training source=MS COCO2022.06 | 52 | |
| BiLSTM+VGGTraining=VG2018.11 | 50.18 | |
| MGBackbone=BiLSTM+VGG, Training source=VG2022.06 | 50.18 | |
| ELMO+VGGTraining=VG2018.11 | 48.76 | |
| MGBackbone=ELMo+VGG, Training source=VG2022.06 | 48.76 | |
| ELMo+VGGTraining=MSCOCO2018.11 | 47.94 | |
| MGBackbone=ELMo+VGG, Training source=MS COCO2022.06 | 47.94 | |
| BiLSTM+VGGTraining=MSCOCO2018.11 | 46.99 | |
| MGBackbone=BiLSTM+VGG, Training source=MS COCO2022.06 | 46.99 | |
| SSSSettings=VGG, Training=VG2018.11 | 30.03 | |
| SSSBackbone=VGG, Training source=VG2022.06 | 30.03 | |
| VGLSSettings=VGG, Training=MSCOCO2018.11 | 24.4 | |
| Baseline (Center)Settings=Center2018.11 | 20.55 | |
| Baseline CenterBackbone=Center, Training source=VG2022.06 | 20.55 | |
| Baseline CenterBackbone=Center, Training source=MS COCO2022.06 | 20.55 | |
| TDSettings=Inception-2, Training=VG2018.11 | 19.31 | |
| TDBackbone=Inception-2, Training source=VG2022.06 | 19.31 | |
| FCVCSettings=VGG, Training=MSCOCO2018.11 | 14.03 | |
| FCVCBackbone=VGG, Training source=MS COCO2022.06 | 14.03 | |
| Baseline (Random)Settings=Random2018.11 | 11.15 | |
| Baseline RandomBackbone=Random, Training source=VG2022.06 | 11.15 | |
| Baseline RandomBackbone=Random, Training source=MS COCO2022.06 | 11.15 |