Papers › Flow Guided Recurrent Neural Encoder for Video Salient Object Detection

Flow Guided Recurrent Neural Encoder for Video Salient Object Detection

1 Jun 2018CVPR 2018 6archive 2025-07-28

Guanbin Li, Yuan Xie, Tianhao Wei, Keze Wang, Liang Lin

Image saliency detection has recently witnessed significant progress due to deep convolutional neural networks. However, extending state-of-the-art saliency detectors from image to video is challenging. The performance of salient object detection suffers from object or camera motion and the dramatic change of the appearance contrast in videos. In this paper, we present flow guided recurrent neural encoder(FGRNE), an accurate and end-to-end learning framework for video salient object detection. It works by enhancing the temporal coherence of the per-frame feature by exploiting both motion information in terms of optical flow and sequential feature evolution encoding in terms of LSTM networks. It can be considered as a universal framework to extend any FCN based static saliency detector to video salient object detection. Intensive experimental results verify the effectiveness of each part of FGRNE and confirm that our proposed method significantly outperforms state-of-the-art methods on the public benchmarks of DAVIS and FBMS.

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

ObjectObject DetectionOptical Flow EstimationRGB Salient Object DetectionSaliency DetectionSalient Object DetectionVideo Salient Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Salient Object Detection DAVIS-2016 FGRN AVERAGE MAE 0.043 #7 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 FGRN MAX E-MEASURE 0.917 #7 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 FGRN MAX F-MEASURE 0.783 #7 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 FGRN S-Measure 0.838 #7 of 11 Archive leaderboard report
Video Salient Object Detection DAVSOD-Difficult20 FGRN Average MAE 0.131 #2 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Difficult20 FGRN S-Measure 0.608 #2 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Difficult20 FGRN max E-measure 0.698 #2 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 FGRN Average MAE 0.126 #3 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 FGRN S-Measure 0.638 #3 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-Normal25 FGRN max E-measure 0.700 #3 of 8 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 FGRN Average MAE 0.095 #4 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 FGRN S-Measure 0.701 #4 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 FGRN max E-Measure 0.765 #4 of 9 Archive leaderboard report
Video Salient Object Detection DAVSOD-easy35 FGRN max F-Measure 0.589 #4 of 9 Archive leaderboard report
Video Salient Object Detection FBMS-59 FGRN AVERAGE MAE 0.088 #7 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 FGRN MAX E-MEASURE 0.863 #7 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 FGRN MAX F-MEASURE 0.767 #7 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 FGRN S-Measure 0.809 #7 of 16 Archive leaderboard report
Video Salient Object Detection MCL FGRN AVERAGE MAE 0.044 #4 of 8 Archive leaderboard report
Video Salient Object Detection MCL FGRN MAX E-MEASURE 0.817 #4 of 8 Archive leaderboard report
Video Salient Object Detection MCL FGRN MAX F-MEASURE 0.625 #4 of 8 Archive leaderboard report
Video Salient Object Detection MCL FGRN S-Measure 0.709 #4 of 8 Archive leaderboard report
Video Salient Object Detection UVSD FGRN Average MAE 0.042 #3 of 8 Archive leaderboard report
Video Salient Object Detection UVSD FGRN S-Measure 0.745 #3 of 8 Archive leaderboard report
Video Salient Object Detection UVSD FGRN max E-measure 0.887 #3 of 8 Archive leaderboard report
Video Salient Object Detection VOS-T FGRN Average MAE 0.097 #5 of 9 Archive leaderboard report
Video Salient Object Detection VOS-T FGRN S-Measure 0.715 #5 of 9 Archive leaderboard report
Video Salient Object Detection VOS-T FGRN max E-measure 0.797 #5 of 9 Archive leaderboard report
Video Salient Object Detection ViSal FGRN Average MAE 0.045 #5 of 10 Archive leaderboard report
Video Salient Object Detection ViSal FGRN S-Measure 0.861 #5 of 10 Archive leaderboard report
Video Salient Object Detection ViSal FGRN max E-measure 0.945 #5 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.

Methods

ConvolutionFCNLSTMMax PoolingSigmoid ActivationTanh Activation

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