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 2130 of 268 papers

TitleStatusHype
Does Text Attract Attention on E-Commerce Images: A Novel Saliency Prediction Dataset and MethodCode1
Learning From Pixel-Level Noisy Label: A New Perspective for Light Field Saliency DetectionCode1
Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face VideosCode1
MaskSplit: Self-supervised Meta-learning for Few-shot Semantic SegmentationCode1
TranSalNet: Towards perceptually relevant visual saliency predictionCode1
Spatio-Temporal Self-Attention Network for Video Saliency PredictionCode1
Specificity-preserving RGB-D Saliency DetectionCode1
DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modelingCode1
Generative Transformer for Accurate and Reliable Salient Object DetectionCode1
BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object DetectionCode1
Show:102550
← PrevPage 3 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