Zero Shot Action Recognition On Activitynet
Metrics
Top-1 Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Top-1 Accuracy |
|---|---|
| cross-modal-representation-learning-for-zero | 32.5 |
| locate-gat-modeling-multi-scale-local-context | 73.8 |
| transferring-textual-knowledge-for-visual | 84.6 |
| rethinking-zero-shot-video-classification-end | 26.6 |
| bidirectional-cross-modal-knowledge | 86.2 |