SOTAVerified

Scanpath prediction

Learning to Predict Sequences of Human Fixations.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 34 papers

TitleStatusHype
OAT: Object-Level Attention Transformer for Gaze Scanpath PredictionCode0
Pathformer3D: A 3D Scanpath Transformer for 360° ImagesCode0
Predicting Visual Attention in Graphic Design Documents—0
Multimodal Learning and Cognitive Processes in Radiology: MedGaze for Chest X-ray Scanpath Prediction—0
Unified Dynamic Scanpath Predictors Outperform Individually Trained Neural Models—0
Beyond Average: Individualized Visual Scanpath Prediction—0
DiffGaze: A Diffusion Model for Continuous Gaze Sequence Generation on 360° Images—0
Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors—0
Scanpath Prediction in Panoramic Videos via Expected Code Length Minimization—0
An Inter-observer consistent deep adversarial training for visual scanpath prediction—0
Show:102550
← PrevPage 2 of 4Next →
All datasetsCapMIT1003Coutrot Dataset 1FixaTons

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NevaClipSBTDE0.38—Unverified
2G-EymolSBTDE0.34—Unverified
#ModelMetricClaimedVerifiedStatus
1G-EYMOLScaled time-delay embeddings0.86—Unverified
#ModelMetricClaimedVerifiedStatus
1G-EYMOLScaled time-delay embeddings0.85—Unverified