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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 141–150 of 268 papers

TitleStatusHype
Ubernet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory—0
Ultrasound Image Representation Learning by Modeling Sonographer Visual Attention—0
Understanding Low- and High-Level Contributions to Fixation Prediction—0
Noise Perturbation for Saliency Prediction with Psychophysical Synthetic Images—0
Unified Dynamic Scanpath Predictors Outperform Individually Trained Neural Models—0
UniST: Towards Unifying Saliency Transformer for Video Saliency Prediction and Detection—0
Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation—0
ViDaS Video Depth-aware Saliency Network—0
Video Saliency Detection by 3D Convolutional Neural Networks—0
Visual Attention driven by Convolutional Features—0
Show:102550
← PrevPage 15 of 27Next →
All datasetsSALECISALICONMIT300CAT2000

Benchmark Results

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