Papers › Unsupervised Video Object Segmentation with Motion-based Bilateral Networks

Unsupervised Video Object Segmentation with Motion-based Bilateral Networks

1 Sep 2018ECCV 2018 9archive 2025-07-28

Siyang Li, Bryan Seybold, Alexey Vorobyov, Xuejing Lei, C. -C. Jay Kuo

In this work, we study the unsupervised video object segmentation problem where moving objects are segmented without prior knowledge of these objects. First, we propose a motion-based bilateral network to estimate the background based on the motion pattern of non-object regions. The bilateral network reduces false positive regions by accurately identifying background objects. Then, we integrate the background estimate from the bilateral network with instance embeddings into a graph, which allows multiple frame reasoning with graph edges linking pixels from different frames. We classify graph nodes by defining and minimizing a cost function, and segment the video frames based on the node labels. The proposed method outperforms previous state-of-the-art unsupervised video object segmentation methods against the DAVIS 2016 and the FBMS-59 datasets.

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

ObjectSegmentationSemantic SegmentationUnsupervised Video Object SegmentationVideo Object SegmentationVideo Salient Object DetectionVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Salient Object Detection DAVIS-2016 MBNM AVERAGE MAE 0.031 #4 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 MBNM MAX E-MEASURE 0.966 #4 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 MBNM MAX F-MEASURE 0.862 #4 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 MBNM S-Measure 0.887 #4 of 11 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 MBNM Average MAE 0.127 #4 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 MBNM S-Measure 0.597 #4 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 MBNM max E-measure 0.665 #4 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 MBNM Average MAE 0.109 #5 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 MBNM S-Measure 0.646 #5 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 MBNM max E-Measure 0.694 #5 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 MBNM max F-Measure 0.506 #5 of 9 Archive leaderboard report
Video Salient Object Detection FBMS-59 MBNM AVERAGE MAE 0.047 #5 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 MBNM MAX E-MEASURE 0.892 #5 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 MBNM MAX F-MEASURE 0.816 #5 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 MBNM S-Measure 0.857 #5 of 16 Archive leaderboard report
Video Salient Object Detection MCL MBNM AVERAGE MAE 0.119 #3 of 8 Archive leaderboard report
Video Salient Object Detection MCL MBNM MAX E-MEASURE 0.858 #3 of 8 Archive leaderboard report
Video Salient Object Detection MCL MBNM MAX F-MEASURE 0.698 #3 of 8 Archive leaderboard report
Video Salient Object Detection MCL MBNM S-Measure 0.755 #3 of 8 Archive leaderboard report
Video Salient Object Detection SegTrack v2 MBNM AVERAGE MAE 0.026 #4 of 8 Archive leaderboard report
Video Salient Object Detection SegTrack v2 MBNM MAX F-MEASURE 0.716 #4 of 8 Archive leaderboard report
Video Salient Object Detection SegTrack v2 MBNM S-Measure 0.809 #4 of 8 Archive leaderboard report
Video Salient Object Detection SegTrack v2 MBNM max E-measure 0.878 #4 of 8 Archive leaderboard report
Video Salient Object Detection UVSD MBNM Average MAE 0.079 #4 of 8 Archive leaderboard report
Video Salient Object Detection UVSD MBNM S-Measure 0.698 #4 of 8 Archive leaderboard report
Video Salient Object Detection UVSD MBNM max E-measure 0.776 #4 of 8 Archive leaderboard report
Video Salient Object Detection VOS-T MBNM Average MAE 0.099 #4 of 9 Archive leaderboard report
Video Salient Object Detection VOS-T MBNM S-Measure 0.742 #4 of 9 Archive leaderboard report
Video Salient Object Detection VOS-T MBNM max E-measure 0.797 #4 of 9 Archive leaderboard report
Video Salient Object Detection ViSal MBNM Average MAE 0.047 #6 of 10 Archive leaderboard report
Video Salient Object Detection ViSal MBNM S-Measure 0.857 #6 of 10 Archive leaderboard report
Video Salient Object Detection ViSal MBNM max E-measure 0.892 #6 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