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 111120 of 268 papers

TitleStatusHype
Human Detection and Tracking for Video Surveillance A Cognitive Science Approach0
FBLNet: FeedBack Loop Network for Driver Attention Prediction0
ITSELF: Iterative Saliency Estimation fLexible Framework0
Dual Domain-Adversarial Learning for Audio-Visual Saliency Prediction0
DTFSal: Audio-Visual Dynamic Token Fusion for Video Saliency Prediction0
Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images0
CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion0
"Looking at the Right Stuff" - Guided Semantic-Gaze for Autonomous Driving0
DSAL-GAN: Denoising based Saliency Prediction with Generative Adversarial Networks0
Distilling Localization for Self-Supervised Representation Learning0
Show:102550
← PrevPage 12 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