Papers › Time-Mapping Using Space-Time Saliency

Time-Mapping Using Space-Time Saliency

1 Jun 2014CVPR 2014 6archive 2025-07-28

Feng Zhou, Sing Bing Kang, Michael F. Cohen

We describe a new approach for generating regular-speed, low-frame-rate (LFR) video from a high-frame-rate (HFR) input while preserving the important moments in the original. We call this time-mapping, a time-based analogy to high dynamic range to low dynamic range spatial tone-mapping. Our approach makes these contributions: (1) a robust space-time saliency method for evaluating visual importance, (2) a re-timing technique to temporally resample based on frame importance, and (3) temporal filters to enhance the rendering of salient motion. Results of our space-time saliency method on a benchmark dataset show it is state-of-the-art. In addition, the benefits of our approach to HFR-to-LFR time-mapping over more direct methods are demonstrated in a user study.

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

Tone MappingVideo Salient Object Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Salient Object Detection DAVIS-2016 TIMP AVERAGE MAE 0.185 #10 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 TIMP MAX E-MEASURE 0.680 #10 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 TIMP S-Measure 0.574 #10 of 11 Archive leaderboard report
Video Salient Object Detection DAVSOD-Difficult20 TIMP Average MAE 0.190 #6 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Difficult20 TIMP S-Measure 0.530 #6 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Difficult20 TIMP max E-measure 0.665 #6 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 TIMP Average MAE 0.245 #7 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 TIMP S-Measure 0.503 #7 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 TIMP max E-measure 0.616 #7 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 TIMP Average MAE 0.206 #8 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 TIMP S-Measure 0.534 #8 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 TIMP max E-Measure 0.582 #8 of 9 Archive leaderboard report
Video Salient Object Detection FBMS-59 TIMP AVERAGE MAE 0.192 #16 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 TIMP MAX F-MEASURE 0.465 #16 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 TIMP S-Measure 0.576 #16 of 16 Archive leaderboard report
Video Salient Object Detection UVSD TIMP Average MAE 0.171 #8 of 8 Archive leaderboard report
Video Salient Object Detection UVSD TIMP S-Measure 0.541 #8 of 8 Archive leaderboard report
Video Salient Object Detection UVSD TIMP max E-measure 0.662 #8 of 8 Archive leaderboard report
Video Salient Object Detection VOS-T TIMP Average MAE 0.192 #9 of 9 Archive leaderboard report
Video Salient Object Detection VOS-T TIMP S-Measure 0.546 #9 of 9 Archive leaderboard report
Video Salient Object Detection VOS-T TIMP max E-measure 0.640 #9 of 9 Archive leaderboard report
Video Salient Object Detection ViSal TIMP Average MAE 0.170 #10 of 10 Archive leaderboard report
Video Salient Object Detection ViSal TIMP S-Measure 0.612 #10 of 10 Archive leaderboard report
Video Salient Object Detection ViSal TIMP max E-measure 0.743 #10 of 10 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