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 221230 of 268 papers

TitleStatusHype
Fast Underwater Image Enhancement for Improved Visual PerceptionCode0
Faster gaze prediction with dense networks and Fisher pruningCode0
Bridging the Gap Between Saliency Prediction and Image Quality AssessmentCode0
DNA: Deeply-supervised Nonlinear Aggregation for Salient Object DetectionCode0
Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagationCode0
PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency DetectionCode0
Predicting Gaze in Egocentric Video by Learning Task-dependent Attention TransitionCode0
Predicting Human Eye Fixations via an LSTM-based Saliency Attentive ModelCode0
Predicting Salient Face in Multiple-Face VideosCode0
Predicting Video Saliency with Object-to-Motion CNN and Two-layer Convolutional LSTMCode0
Show:102550
← PrevPage 23 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