Papers › Shifting More Attention to Video Salient Object Detection

Shifting More Attention to Video Salient Object Detection

1 Jun 2019CVPR 2019 6archive 2025-07-28

Deng-Ping Fan, Wenguan Wang, Ming-Ming Cheng, Jianbing Shen

The last decade has witnessed a growing interest in video salient object detection (VSOD). However, the research community long-term lacked a well-established VSOD dataset representative of real dynamic scenes with high-quality annotations. To address this issue, we elaborately collected a visual-attention-consistent Densely Annotated VSOD (DAVSOD) dataset, which contains 226 videos with 23,938 frames that cover diverse realistic-scenes, objects, instances and motions. With corresponding real human eye-fixation data, we obtain precise ground-truths. This is the first work that explicitly emphasizes the challenge of saliency shift, i.e., the video salient object(s) may dynamically change. To further contribute the community a complete benchmark, we systematically assess 17 representative VSOD algorithms over seven existing VSOD datasets and our DAVSOD with totally 84K frames (largest-scale). Utilizing three famous metrics, we then present a comprehensive and insightful performance analysis. Furthermore, we propose a baseline model. It is equipped with a saliency shift- aware convLSTM, which can efficiently capture video saliency dynamics through learning human attention-shift behavior. Extensive experiments open up promising future directions for model development and comparison.

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

ObjectObject DetectionRGB Salient Object DetectionSalient Object DetectionVideo Object SegmentationVideo Salient Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Salient Object Detection DAVIS-2016 SSAV AVERAGE MAE 0.028 #3 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 SSAV MAX E-MEASURE 0.948 #3 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 SSAV MAX F-MEASURE 0.861 #3 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 SSAV S-Measure 0.893 #3 of 11 Archive leaderboard report
Video Salient Object Detection DAVSOD-Difficult20 SSAV Average MAE 0.114 #1 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Difficult20 SSAV S-Measure 0.619 #1 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Difficult20 SSAV max E-measure 0.696 #1 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 SSAV Average MAE 0.117 #1 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 SSAV S-Measure 0.661 #1 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 SSAV max E-measure 0.723 #1 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 SSAV Average MAE 0.084 #2 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 SSAV S-Measure 0.755 #2 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 SSAV max E-Measure 0.806 #2 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 SSAV max F-Measure 0.659 #2 of 9 Archive leaderboard report
Video Salient Object Detection FBMS-59 SSAV AVERAGE MAE 0.040 #3 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 SSAV MAX E-MEASURE 0.926 #3 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 SSAV MAX F-MEASURE 0.865 #3 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 SSAV S-Measure 0.879 #3 of 16 Archive leaderboard report
Video Salient Object Detection MCL SSAV AVERAGE MAE 0.026 #2 of 8 Archive leaderboard report
Video Salient Object Detection MCL SSAV MAX E-MEASURE 0.889 #2 of 8 Archive leaderboard report
Video Salient Object Detection MCL SSAV MAX F-MEASURE 0.773 #2 of 8 Archive leaderboard report
Video Salient Object Detection MCL SSAV S-Measure 0.819 #2 of 8 Archive leaderboard report
Video Salient Object Detection SegTrack v2 SSAV AVERAGE MAE 0.023 #3 of 8 Archive leaderboard report
Video Salient Object Detection SegTrack v2 SSAV MAX F-MEASURE 0.801 #3 of 8 Archive leaderboard report
Video Salient Object Detection SegTrack v2 SSAV S-Measure 0.850 #3 of 8 Archive leaderboard report
Video Salient Object Detection SegTrack v2 SSAV max E-measure 0.917 #3 of 8 Archive leaderboard report
Video Salient Object Detection UVSD SSAV Average MAE 0.025 #2 of 8 Archive leaderboard report
Video Salient Object Detection UVSD SSAV S-Measure 0.860 #2 of 8 Archive leaderboard report
Video Salient Object Detection UVSD SSAV max E-measure 0.939 #2 of 8 Archive leaderboard report
Video Salient Object Detection VOS-T SSAV Average MAE 0.074 #2 of 9 Archive leaderboard report
Video Salient Object Detection VOS-T SSAV S-Measure 0.819 #2 of 9 Archive leaderboard report
Video Salient Object Detection VOS-T SSAV max E-measure 0.839 #2 of 9 Archive leaderboard report
Video Salient Object Detection ViSal SSAV Average MAE 0.021 #3 of 10 Archive leaderboard report
Video Salient Object Detection ViSal SSAV S-Measure 0.942 #3 of 10 Archive leaderboard report
Video Salient Object Detection ViSal SSAV max E-measure 0.980 #3 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