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
Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNetCode1
Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray ImagesCode1
Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified BenchmarkCode1
Panoramic Vision Transformer for Saliency Detection in 360° VideosCode1
RSKDD-Net: Random Sample-based Keypoint Detector and DescriptorCode1
Select, Supplement and Focus for RGB-D Saliency DetectionCode1
Specificity-preserving RGB-D Saliency DetectionCode1
Spherical Vision Transformer for 360-degree Video Saliency PredictionCode1
Spatio-Temporal Self-Attention Network for Video Saliency PredictionCode1
Video Saliency Prediction Using Enhanced Spatiotemporal Alignment NetworkCode1
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