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 5160 of 268 papers

TitleStatusHype
Multi-source weak supervision for saliency detectionCode0
Noise-Aware Video Saliency PredictionCode0
Modeling Bottom-Up and Top-Down Attention with a Neurodynamic Model of V1Code0
Modeling Object Dissimilarity for Deep Saliency PredictionCode0
DAVE: A Deep Audio-Visual Embedding for Dynamic Saliency PredictionCode0
How is Visual Attention Influenced by Text Guidance? Database and ModelCode0
CSPENet: Contour-Aware and Saliency Priors Embedding Network for Infrared Small Target DetectionCode0
Gravitational Laws of Focus of AttentionCode0
Correlation of Object Detection Performance with Visual Saliency and Depth EstimationCode0
Contextual Encoder-Decoder Network for Visual Saliency PredictionCode0
Show:102550
← PrevPage 6 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