Video Saliency Detection On Msu Video
평가 지표
AUC-J
CC
FPS
KLDiv
NSS
SIM
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | AUC-J | CC | FPS | KLDiv | NSS | SIM |
|---|---|---|---|---|---|---|
| video-saliency-detection-with-domain-adaption | 0.844 | 0.707 | 24.51 | 0.545 | 1.89 | 0.615 |
| a-model-of-saliency-based-visual-attention | 0.811 | 0.572 | 2.23 | 0.799 | 1.34 | 0.544 |
| visual-saliency-based-on-scale-space-analysis | 0.814 | 0.577 | 3.63 | 0.698 | 1.35 | 0.550 |
| a-dilated-inception-network-for-visual | 0.858 | 0.671 | 4.85 | 0.575 | 1.85 | 0.592 |
| graph-based-visual-saliency | 0.810 | 0.572 | 1.93 | 0.709 | 1.33 | 0.546 |
| simple-vs-complex-temporal-recurrences-for | 0.821 | 0.636 | 32.97 | 0.647 | 1.63 | 0.571 |
| video-saliency-prediction-using-enhanced | 0.841 | 0.665 | 3.35 | 0.583 | 1.81 | 0.591 |
| revisiting-video-saliency-a-large-scale | 0.839 | 0.651 | 4.18 | 0.593 | 1.71 | 0.586 |
| avinet-diving-deep-into-audio-visual-saliency | 0.864 | 0.733 | 1.10 | 0.497 | 2.13 | 0.627 |
| tased-net-temporally-aggregating-spatial | 0.852 | 0.710 | 1.85 | 0.538 | 1.96 | 0.610 |
| deepvs-a-deep-learning-based-video-saliency | 0.804 | 0.586 | 3.29 | 0.707 | 1.44 | 0.548 |
| unified-image-and-video-saliency-modeling | 0.858 | 0.707 | 70.46 | 0.536 | 2.03 | 0.609 |
| contextual-encoder-decoder-network-for-visual | 0.852 | 0.690 | 1.28 | 0.537 | 1.82 | 0.607 |
| gasp-gated-attention-for-saliency-prediction-1 | 0.810 | 0.613 | 3.77 | 0.687 | 1.57 | 0.557 |