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 171180 of 268 papers

TitleStatusHype
Model-guided Multi-path Knowledge Aggregation for Aerial Saliency Prediction0
Visual Saliency Maps Can Apply to Facial Expression Recognition0
Semantic and Contrast-Aware Saliency0
Bottom-up Attention, Models of0
Saliency Prediction in the Deep Learning Era: Successes, Limitations, and Future Challenges0
Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation0
Learning Saliency Prediction From Sparse Fixation Pixel Map0
DeepVS: A Deep Learning Based Video Saliency Prediction ApproachCode0
Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web PriorCode0
Task-driven Webpage Saliency0
Show:102550
← PrevPage 18 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