DEM

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

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

Computer Vision2 results

Zero-Shot Action RecognitiononKinetics
Top-1 Accuracy· 2016-11-15
23.6
best: 78.1 (TC-CLIP)
SOTA
Learning a Deep Embedding Model for Zero-Shot Learning arXiv:1611.05088
Zero-Shot Action RecognitiononKinetics
Top-5 Accuracy· 2016-11-15
49.5
best: 95.7 (TC-CLIP)
Learning a Deep Embedding Model for Zero-Shot Learning arXiv:1611.05088