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 7180 of 268 papers

TitleStatusHype
Salient Object Detection From Arbitrary ModalitiesCode0
Unified Dynamic Scanpath Predictors Outperform Individually Trained Neural Models0
Shifting Focus with HCEye: Exploring the Dynamics of Visual Highlighting and Cognitive Load on User Attention and Saliency Prediction0
How is Visual Attention Influenced by Text Guidance? Database and ModelCode0
Separated Attention: An Improved Cycle GAN Based Under Water Image Enhancement Method0
SalFoM: Dynamic Saliency Prediction with Video Foundation Models0
GreenSaliency: A Lightweight and Efficient Image Saliency Detection Method0
Selective Attention-based Modulation for Continual LearningCode0
DiffGaze: A Diffusion Model for Continuous Gaze Sequence Generation on 360° Images0
Learning User Embeddings from Human Gaze for Personalised Saliency Prediction0
Show:102550
← PrevPage 8 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