SJE(Word Embedding)

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Zero-Shot Action RecognitiononKinetics
Top-1 Accuracy· 2014-09-30
22.3
best: 78.1 (TC-CLIP)
SOTA
Evaluation of Output Embeddings for Fine-Grained Image Classification arXiv:1409.8403
Zero-Shot Action RecognitiononKinetics
Top-5 Accuracy· 2014-09-30
48.2
best: 95.7 (TC-CLIP)
SOTA
Evaluation of Output Embeddings for Fine-Grained Image Classification arXiv:1409.8403
Zero-Shot Action RecognitiononUCF101
Top-1 Accuracy· 2014-09-30
9.9
best: 92.8 (OTI(ViT-L/14))
Evaluation of Output Embeddings for Fine-Grained Image Classification arXiv:1409.8403
Zero-Shot Action RecognitiononOlympics
Top-1 Accuracy· 2014-09-30
28.6
best: 68.7 (SPOT)
Evaluation of Output Embeddings for Fine-Grained Image Classification arXiv:1409.8403