Multimodal Activity Recognition On Moments In
المقاييس
Top-1 (%)
Top-5 (%)
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
اسم النموذج | Top-1 (%) | Top-5 (%) | Paper Title | Repository |
|---|---|---|---|---|
| TRN-Multiscale | 28.27 | 53.87 | Moments in Time Dataset: one million videos for event understanding | |
| I3D | 29.51 | 56.06 | Moments in Time Dataset: one million videos for event understanding | |
| SoundNet | 7.60 | 18.00 | Moments in Time Dataset: one million videos for event understanding | |
| AssembleNet | 34.27 | 62.71 | AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures | |
| Ensemble (SVM) | 31.16 | 57.67 | Moments in Time Dataset: one million videos for event understanding | |
| TSN-Flow | 15.71 | 34.65 | Moments in Time Dataset: one million videos for event understanding |
0 of 6 row(s) selected.