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 81–90 of 268 papers

TitleStatusHype
A Modified Word Saliency-Based Adversarial Attack on Text Classification Models—0
DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction—0
Transformer-based Video Saliency Prediction with High Temporal Dimension Decoding—0
Learning Saliency From Fixations—0
Audio-visual Saliency for Omnidirectional Videos—0
XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision—0
What Do Deep Saliency Models Learn about Visual Attention?Code0
UniST: Towards Unifying Saliency Transformer for Video Saliency Prediction and Detection—0
Attention for Robot Touch: Tactile Saliency Prediction for Robust Sim-to-Real Tactile Control—0
Few-shot Personalized Saliency Prediction Based on Inter-personnel Gaze Patterns—0
Show:102550
← PrevPage 9 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