Human attention prediction on BDD-A (test)
1.24KL Divergence (Mean)BDD-A prediction model (default)
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| BDD-A prediction model (default)Sampling Strategy=default, Output Size=64x362017.11 | 1.24 | — | 0.58 | — | |
| BDD-A prediction model (HWS)Sampling Strategy=Human Weighted Sampling (HWS), Output Size=64x362017.11 | 1.24 | — | 0.59 | — | |
| SALICONFine-tuned=true, Implementation=Open source [26], Output Size=64x36 (scaled)2017.11 | 1.41 | — | 0.53 | — | |
| Averaged attention baselineDescription=Predicts the averaged human attention map of training videos2017.11 | 1.5 | — | 0.46 | — | |
| DR(eye)VEPre-trained=true, Fine-tuned=false, Output Size=64x36 (scaled)2017.11 | 1.95 | — | 0.5 | — |