SOTAVerified

Saliency Prediction

A saliency map is a model that predicts eye fixations on a visual scene. Saliency prediction is informed by the human visual attention mechanism and predicts the possibility of the human eyes to stay in a certain position in the scene.

Papers

Showing 4150 of 268 papers

TitleStatusHype
Select, Supplement and Focus for RGB-D Saliency DetectionCode1
Semantic Segmentation of Underwater Imagery: Dataset and BenchmarkCode1
Unified Image and Video Saliency ModelingCode1
Tidying Deep Saliency Prediction ArchitecturesCode1
Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual PerceptionCode1
STAViS: Spatio-Temporal AudioVisual Saliency NetworkCode1
Video Saliency Prediction Using Enhanced Spatiotemporal Alignment NetworkCode1
BASNet: Boundary-Aware Salient Object DetectionCode1
How is Gaze Influenced by Image Transformations? Dataset and ModelCode1
Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNetCode1
Show:102550
← PrevPage 5 of 27Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TransalnetKL0.87Unverified
2TempSALKL0.71Unverified
3SSwin transformerKL0.65Unverified
4ECT-SALKL0.58Unverified
5SUMKL0.47Unverified
#ModelMetricClaimedVerifiedStatus
1SUMAUC0.88Unverified
2SalNAS-XL + Self-KDAUC0.87Unverified
3TempSALAUC0.87Unverified
4MDS-ViTNetAUC0.87Unverified
5TranSalNetAUC0.87Unverified
#ModelMetricClaimedVerifiedStatus
1SUMAUC-Judd0.91Unverified
2TranSalNetAUC-Judd0.87Unverified
#ModelMetricClaimedVerifiedStatus
1SUMKL0.27Unverified