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 226–250 of 268 papers

TitleStatusHype
How Many Bits Does it Take for a Stimulus to Be Salient?—0
Human Detection and Tracking for Video Surveillance A Cognitive Science Approach—0
FBLNet: FeedBack Loop Network for Driver Attention Prediction—0
ITSELF: Iterative Saliency Estimation fLexible Framework—0
Label Consistent Quadratic Surrogate Model for Visual Saliency Prediction—0
Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images—0
Learning Category-level Shape Saliency via Deep Implicit Surface Networks—0
Learning Gaze Transitions from Depth to Improve Video Saliency Estimation—0
Learning Gaze Transitions From Depth to Improve Video Saliency Estimation—0
Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction—0
Learning Saliency From Fixations—0
Learning Saliency Prediction From Sparse Fixation Pixel Map—0
Learning to Explore Intrinsic Saliency for Stereoscopic Video—0
Learning to Predict Saliency on Face Images—0
Learning User Embeddings from Human Gaze for Personalised Saliency Prediction—0
Learning Video Saliency from Human Gaze Using Candidate Selection—0
Light Field Saliency Detection With Dual Local Graph Learning and Reciprocative Guidance—0
LMME3DHF: Benchmarking and Evaluating Multimodal 3D Human Face Generation with LMMs—0
Looking at the right stuff: Guided semantic-gaze for autonomous driving—0
"Looking at the Right Stuff" - Guided Semantic-Gaze for Autonomous Driving—0
Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues—0
Modeling Saliency Dataset Bias—0
MRGAN360: Multi-stage Recurrent Generative Adversarial Network for 360 Degree Image Saliency Prediction—0
Part Discovery from Partial Correspondence—0
Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention—0
Show:102550
← PrevPage 10 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