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 51–75 of 268 papers

TitleStatusHype
Few-shot Personalized Saliency Prediction Based on Inter-personnel Gaze Patterns—0
Teaching AI to Teach: Leveraging Limited Human Salience Data Into Unlimited Saliency-Based Training—0
ViDaS Video Depth-aware Saliency Network—0
A positive feedback method based on F-measure value for Salient Object DetectionCode0
MRGAN360: Multi-stage Recurrent Generative Adversarial Network for 360 Degree Image Saliency Prediction—0
CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspective—0
Deep Saliency Mapping for 3D Meshes and ApplicationsCode0
Semantic Segmentation Enhanced Transformer Model for Human Attention Prediction—0
TinyHD: Efficient Video Saliency Prediction with Heterogeneous Decoders using Hierarchical Maps DistillationCode1
TempSAL -- Uncovering Temporal Information for Deep Saliency PredictionCode1
Co-Salient Object Detection With Uncertainty-Aware Group Exchange-Masking—0
CASP-Net: Rethinking Video Saliency Prediction From an Audio-Visual Consistency Perceptual Perspective—0
TempSAL - Uncovering Temporal Information for Deep Saliency PredictionCode1
FBLNet: FeedBack Loop Network for Driver Attention Prediction—0
Context-empowered Visual Attention Prediction in Pedestrian Scenarios—0
Panoramic Vision Transformer for Saliency Detection in 360° VideosCode1
Saliency-based Multiple Region of Interest Detection from a Single 360° image—0
Dual Domain-Adversarial Learning for Audio-Visual Saliency Prediction—0
Rethinking gradient weights' influence over saliency map estimation—0
SiaTrans: Siamese Transformer Network for RGB-D Salient Object Detection with Depth Image Classification—0
Clustered Saliency Prediction—0
GASP: Gated Attention For Saliency PredictionCode1
Dual Swin-Transformer based Mutual Interactive Network for RGB-D Salient Object Detection—0
Learning from Pixel-Level Noisy Label : A New Perspective for Light Field Saliency DetectionCode1
An Energy-Based Prior for Generative SaliencyCode1
Show:102550
← PrevPage 3 of 11Next →
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