Papers › Graph-Based Visual Saliency

Graph-Based Visual Saliency

4 Dec 2006Advances in Neural Information Processing Systems 19 2006 12archive 2025-07-28

Jonathan Harel, Christof Koch, Pietro Perona

A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed. It consists of two steps: rst forming activation maps on certain feature channels, and then normalizing them in a way which highlights conspicuity and admits combination with other maps. The model is simple, and biologically plausible insofar as it is naturally parallelized. This model powerfully predicts human xations on 749 variations of 108 natural images, achieving 98% of the ROC area of a human-based control, whereas the classical algorithms of Itti & Koch ([2], [3], [4]) achieve only 84%.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Saliency PredictionVideo Saliency Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Saliency Detection MSU Video Saliency Prediction GBVS AUC-J 0.810 #13 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction GBVS CC 0.572 #13 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction GBVS FPS 1.93 #13 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction GBVS KLDiv 0.709 #13 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction GBVS NSS 1.33 #13 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction GBVS SIM 0.546 #13 of 14 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