Papers › Gravitational Laws of Focus of Attention

Gravitational Laws of Focus of Attention

4 Jun 2019IEEE Transactions on Pattern Analysis and Machine Intelligence 2019 6archive 2025-07-28

Zanca, Dario; Melacci, Stefano; Gori, Marco

The understanding of the mechanisms behind focus of attention in a visual scene is a problem of great interest in visual perception and computer vision. In this paper, we describe a model of scanpath as a dynamic process which can be interpreted as a variational law somehow related to mechanics, where the focus of attention is subject to a gravitational field. The distributed virtual mass that drives eye movements is associated with the presence of details and motion in the video. Unlike most current models, the proposed approach does not estimate directly the saliency map, but the prediction of eye movements allows us to integrate over time the positions of interest. The process of inhibition-of-return is also supported in the same dynamic model with the purpose of simulating fixations and saccades. The differential equations of motion of the proposed model are numerically integrated to simulate scanpaths on both images and videos. Experimental results for the tasks of saliency and scanpath prediction on a wide collection of datasets are presented to support the theory. Top level performances are achieved especially in the prediction of scanpaths, which is the primary purpose of the proposed model.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

PredictionSaliency DetectionSaliency PredictionScanpath prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scanpath prediction Coutrot Dataset 1 G-EYMOL Scaled time-delay embeddings 0.86 #1 of 1 Archive leaderboard report
Scanpath prediction Coutrot Dataset 1 G-EYMOL String-edit distance 23.83 #1 of 1 Archive leaderboard report
Scanpath prediction FixaTons G-EYMOL Scaled time-delay embeddings 0.85 #1 of 1 Archive leaderboard report
Scanpath prediction FixaTons G-EYMOL String-edit distance 3.72 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections