Fine-grained Image Classification on Crowd Activity (test)
87.45mAPKnowledge Mining with Scene Text
Evaluation results
| Method | Links | |
|---|---|---|
| Knowledge Mining with Scene TextVision=ViT, Text Spotter=Google OCR, Embedding=KnowBert2022.03 | 87.45 | |
| Knowledge Mining with Scene TextVision=ViT, Text Spotter=E2E-MLT, Embedding=KnowBert2022.03 | 85.68 | |
| Knowledge Mining with Scene TextVision=ResNet-152, Text Spotter=E2E-MLT, Embedding=KnowBert2022.03 | 81.91 | |
| Mafla et al.Vision=ResNet-152, Text Spotter=Google OCR, Embedding=fastText2022.03 | 79.25 | |
| Mafla et al.Vision=ResNet-152, Text Spotter=SSTR-PHOC, Embedding=FV2022.03 | 77.57 | |
| Mafla et al.Vision=ResNet-152, Text Spotter=SSTR-PHOC, Embedding=FV2022.03 | 77.54 | |
| Mafla et al.Vision=ResNet-152, Text Spotter=SSTR-PHOC, Embedding=PHOC2022.03 | 75.45 | |
| Mafla et al.Vision=ResNet-152, Text Spotter=E2E-MLT, Embedding=fastText2022.03 | 75.31 | |
| Mafla et al.Vision=ResNet-152, Text Spotter=SSTR-PHOC, Embedding=PHOC2022.03 | 73.84 | |
| Mafla et al.Vision=ResNet-152, Text Spotter=E2E-MLT, Embedding=fastText2022.03 | 73.01 | |
| Mafla et al.Vision=ResNet-152, Text Spotter=E2E-MLT, Embedding=GloVe2022.03 | 72.58 |