{"url":"/sota/video-salient-object-detection-on-segtrack-v2","task":{"name":"Video Salient Object Detection","url":"/task/video-salient-object-detection","note":null},"dataset":{"name":"SegTrack v2","url":"/dataset/segtrack-v2-1"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Video salient object detection (VSOD) is significantly essential for understanding the underlying mechanism behind HVS during free-viewing in general and instrumental to a wide range of real-world applications, e.g., video segmentation, video captioning, video compression, autonomous driving, robotic interaction, weakly supervised attention. Besides its academic value and practical significance, VSOD presents great difficulties due to the challenges carried by video data (diverse motion patterns, occlusions, blur, large object deformations, etc.) and the inherent complexity of human visual attention behavior (i.e., selective attention allocation, attention shift) during dynamic scenes. Online benchmark: http://dpfan.net/davsod.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Shifting More Attention to Video Salient Object Detection, CVPR2019-Best Paper Finalist](https://openaccess.thecvf.com/content_CVPR_2019/papers/Fan_Shifting_More_Attention_to_Video_Salient_Object_Detection_CVPR_2019_paper.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["S-Measure","max E-measure","MAX F-MEASURE","AVERAGE MAE"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"S-Measure":null,"max E-measure":null,"MAX F-MEASURE":null,"AVERAGE MAE":"lower"}},"counts":{"rows":8,"rows_with_code":3,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"UFO","metrics":{"AVERAGE MAE":"0.022","MAX F-MEASURE":"0.863","S-Measure":"0.892"},"uses_additional_data":true,"paper_date":"2022-03-09","paper":"/paper/a-unified-transformer-framework-for-group","paper_url":"https://arxiv.org/abs/2203.04708v2","paper_title":"A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection","code":"https://github.com/suyukun666/UFO","n_code_links":1,"syntology":{"n_ran":12,"n_unverified":1,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"PDB","metrics":{"AVERAGE MAE":"0.024","S-Measure":"0.864","max E-measure":"0.935"},"uses_additional_data":true,"paper_date":"2018-09-01","paper":"/paper/pyramid-dilated-deeper-convlstm-for-video","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Hongmei_Song_Pseudo_Pyramid_Deeper_ECCV_2018_paper.html","paper_title":"Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"SSAV","metrics":{"AVERAGE MAE":"0.023","MAX F-MEASURE":"0.801","S-Measure":"0.850","max E-measure":"0.917"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/shifting-more-attention-to-video-salient","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Fan_Shifting_More_Attention_to_Video_Salient_Object_Detection_CVPR_2019_paper.html","paper_title":"Shifting More Attention to Video Salient Object Detection","code":"https://github.com/DengPingFan/DAVSOD","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"MBNM","metrics":{"AVERAGE MAE":"0.026","MAX F-MEASURE":"0.716","S-Measure":"0.809","max E-measure":"0.878"},"uses_additional_data":true,"paper_date":"2018-09-01","paper":"/paper/unsupervised-video-object-segmentation-with-1","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Siyang_Li_Unsupervised_Video_Object_ECCV_2018_paper.html","paper_title":"Unsupervised Video Object Segmentation with Motion-based Bilateral Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"SAGM","metrics":{"AVERAGE MAE":"0.081","S-Measure":"0.719","max E-measure":"0.826"},"uses_additional_data":true,"paper_date":"2015-06-01","paper":"/paper/saliency-aware-geodesic-video-object","paper_url":"http://openaccess.thecvf.com/content_cvpr_2015/html/Wang_Saliency-Aware_Geodesic_Video_2015_CVPR_paper.html","paper_title":"Saliency-Aware Geodesic Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"TIMP","metrics":{"AVERAGE MAE":"0.116","S-Measure":"0.644","max E-measure":"0.768"},"uses_additional_data":true,"paper_date":"2019-07-25","paper":"/paper/time-masking-leveraging-temporal-information","paper_url":"https://arxiv.org/abs/1907.11315v1","paper_title":"Time Masking: Leveraging Temporal Information in Spoken Dialogue Systems","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"MSTM","metrics":{"AVERAGE MAE":"0.114","S-Measure":"0.643","max E-measure":"0.733"},"uses_additional_data":true,"paper_date":"2016-06-01","paper":"/paper/real-time-salient-object-detection-with-a","paper_url":"http://openaccess.thecvf.com/content_cvpr_2016/html/Tu_Real-Time_Salient_Object_CVPR_2016_paper.html","paper_title":"Real-Time Salient Object Detection With a Minimum Spanning Tree","code":"https://github.com/cj4L/MST-python","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"MB+M","metrics":{"AVERAGE MAE":"0.146","S-Measure":"0.618","max E-measure":"0.778"},"uses_additional_data":true,"paper_date":"2015-12-01","paper":"/paper/minimum-barrier-salient-object-detection-at","paper_url":"http://openaccess.thecvf.com/content_iccv_2015/html/Zhang_Minimum_Barrier_Salient_ICCV_2015_paper.html","paper_title":"Minimum Barrier Salient Object Detection at 80 FPS","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,821 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":12,"n_unverified":1,"n_samples":13,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":12,"n_unverified":1,"n_samples":13,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}