Saliency Prediction on DIEM (test)
0.498SIMAViNet(B)
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| AViNet(B)Fusion method=Bilinear2020.12 | 0.498 | — | 0.719 | 0.632 | 2.53 | 0.899 | |
| AViNet(C)Fusion method=Concatenation2020.12 | 0.497 | — | 0.72 | 0.631 | 2.5 | 0.897 | |
| ViNetFine-tuned on audio-visual datasets=true2020.12 | 0.483 | — | 0.723 | 0.626 | 2.47 | 0.898 | |
| STAVIS2020.12 | 0.482 | — | 0.674 | 0.579 | 2.26 | 0.883 | |
| ViNet(NF)Fine-tuned on audio-visual datasets=false, Training Dataset=DHF1K2020.12 | 0.468 | — | 0.695 | 0.571 | 2.28 | 0.886 | |
| TASED-Net2020.12 | 0.461 | — | 0.657 | 0.557 | 2.16 | 0.881 | |
| ACLNet2020.12 | 0.427 | — | 0.622 | 0.522 | 2.02 | 0.869 | |
| Enhanced Spatiotemporal Alignment NetworkTraining setting=(iv), Training sets=DHF1K + HollyWood-2 + UCF sports2020.01 | 0.396 | 0.889 | 0.711 | 0.49 | 2.346 | — | |
| Enhanced Spatiotemporal Alignment NetworkTraining setting=(i), Training sets=DHF1K2020.01 | 0.391 | 0.88 | 0.718 | 0.472 | 2.346 | — | |
| Enhanced Spatiotemporal Alignment NetworkTraining setting=(ii), Training sets=HollyWood-22020.01 | 0.355 | 0.87 | 0.698 | 0.468 | 2.359 | — | |
| STRA-NetModel Category=Dynamic Models, DL-based=true2020.01 | 0.306 | 0.87 | 0.678 | 0.408 | 2.452 | — | |
| Enhanced Spatiotemporal Alignment NetworkTraining setting=(iii), Training sets=UCF sports2020.01 | 0.296 | 0.831 | 0.676 | 0.351 | 1.828 | — | |
| ACLNetModel Category=Dynamic Models, DL-based=true2020.01 | 0.277 | 0.881 | 0.693 | 0.396 | 2.368 | — | |
| Two-streamModel Category=Dynamic Models, DL-based=true2020.01 | 0.256 | 0.859 | 0.682 | 0.366 | 2.171 | — | |
| OM-CNNModel Category=Dynamic Models, DL-based=true2020.01 | 0.238 | 0.857 | 0.693 | 0.371 | 2.235 | — | |
| DVAModel Category=Static Models, DL-based=true2020.01 | 0.237 | 0.868 | 0.721 | 0.386 | 2.347 | — | |
| Shallow-NetModel Category=Static Models, DL-based=true2020.01 | 0.188 | 0.838 | 0.62 | 0.297 | 1.646 | — | |
| SALICONModel Category=Static Models, DL-based=true2020.01 | 0.171 | 0.793 | 0.674 | 0.27 | 1.65 | — | |
| Fang et al.Model Category=Dynamic Models, DL-based=false2020.01 | 0.167 | 0.823 | 0.636 | 0.251 | 1.423 | — | |
| OBDLModel Category=Dynamic Models, DL-based=false2020.01 | 0.165 | 0.762 | 0.694 | 0.221 | 1.289 | — | |
| Deep-NetModel Category=Static Models, DL-based=true2020.01 | 0.164 | 0.849 | 0.697 | 0.291 | 1.65 | — | |
| GBVSModel Category=Static Models, DL-based=false2020.01 | 0.156 | 0.813 | 0.633 | 0.214 | 1.198 | — | |
| Rudoy et al.Model Category=Dynamic Models, DL-based=false2020.01 | 0.15 | 0.775 | 0.618 | 0.26 | 1.39 | — | |
| AWS-DModel Category=Dynamic Models, DL-based=false2020.01 | 0.15 | 0.774 | 0.695 | 0.216 | 1.252 | — | |
| Hou et al.Model Category=Dynamic Models, DL-based=false2020.01 | 0.142 | 0.735 | 0.589 | 0.128 | 0.735 | — | |
| ITTIModel Category=Static Models, DL-based=false2020.01 | 0.132 | 0.791 | 0.653 | 0.196 | 1.103 | — | |
| Seo et al.Model Category=Dynamic Models, DL-based=false2020.01 | 0.13 | 0.723 | 0.568 | 0.116 | 0.665 | — | |
| PQFTModel Category=Dynamic Models, DL-based=false2020.01 | 0.126 | 0.724 | 0.649 | 0.144 | 0.856 | — |