{"url":"/sota/video-saliency-detection-on-msu-video","task":{"name":"Video Saliency Detection","url":"/task/video-saliency-detection","note":null},"dataset":{"name":"MSU Video Saliency Prediction","url":"/dataset/msu-video-saliency-prediction"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Video Saliency Detection is the process of detecting or predicting the most visually important or attention-grabbing regions in video sequence. This regions are where humans most likely focus their attention when watching the video.","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":["SIM","CC","NSS","AUC-J","KLDiv","FPS"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"SIM":null,"CC":null,"NSS":null,"AUC-J":"higher","KLDiv":null,"FPS":null}},"counts":{"rows":14,"rows_with_code":11,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ViNet (dave)","metrics":{"AUC-J":"0.864","CC":"0.733","FPS":"1.10","KLDiv":"0.497","NSS":"2.13","SIM":"0.627"},"uses_additional_data":false,"paper_date":"2020-12-11","paper":"/paper/avinet-diving-deep-into-audio-visual-saliency","paper_url":"https://arxiv.org/abs/2012.06170v3","paper_title":"ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction","code":"https://github.com/samyak0210/ViNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"HD2S","metrics":{"AUC-J":"0.844","CC":"0.707","FPS":"24.51","KLDiv":"0.545","NSS":"1.89","SIM":"0.615"},"uses_additional_data":false,"paper_date":"2020-10-02","paper":"/paper/video-saliency-detection-with-domain-adaption","paper_url":"https://arxiv.org/abs/2010.01220v4","paper_title":"Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction","code":"https://github.com/perceivelab/hd2s","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"TASED-Net","metrics":{"AUC-J":"0.852","CC":"0.710","FPS":"1.85","KLDiv":"0.538","NSS":"1.96","SIM":"0.610"},"uses_additional_data":false,"paper_date":"2019-08-15","paper":"/paper/tased-net-temporally-aggregating-spatial","paper_url":"https://arxiv.org/abs/1908.05786v1","paper_title":"TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection","code":"https://github.com/kylemin/TASED-Net","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"UNISAL (videos)","metrics":{"AUC-J":"0.858","CC":"0.707","FPS":"70.46","KLDiv":"0.536","NSS":"2.03","SIM":"0.609"},"uses_additional_data":false,"paper_date":"2020-03-11","paper":"/paper/unified-image-and-video-saliency-modeling","paper_url":"https://arxiv.org/abs/2003.05477v3","paper_title":"Unified Image and Video Saliency Modeling","code":"https://github.com/rdroste/unisal","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"MSI-Net (dutomron)","metrics":{"AUC-J":"0.852","CC":"0.690","FPS":"1.28","KLDiv":"0.537","NSS":"1.82","SIM":"0.607"},"uses_additional_data":false,"paper_date":"2019-02-18","paper":"/paper/contextual-encoder-decoder-network-for-visual","paper_url":"https://arxiv.org/abs/1902.06634v4","paper_title":"Contextual Encoder-Decoder Network for Visual Saliency Prediction","code":"https://github.com/alexanderkroner/saliency","n_code_links":4,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"DINet","metrics":{"AUC-J":"0.858","CC":"0.671","FPS":"4.85","KLDiv":"0.575","NSS":"1.85","SIM":"0.592"},"uses_additional_data":false,"paper_date":"2019-04-07","paper":"/paper/a-dilated-inception-network-for-visual","paper_url":"https://arxiv.org/abs/1904.03571v2","paper_title":"A Dilated Inception Network for Visual Saliency Prediction","code":"https://github.com/ysyscool/DINet","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"STRA-Net","metrics":{"AUC-J":"0.841","CC":"0.665","FPS":"3.35","KLDiv":"0.583","NSS":"1.81","SIM":"0.591"},"uses_additional_data":false,"paper_date":"2020-01-02","paper":"/paper/video-saliency-prediction-using-enhanced","paper_url":"https://arxiv.org/abs/2001.00292v1","paper_title":"Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network","code":"https://github.com/cj4L/ESAN-VSP","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"ACLNet","metrics":{"AUC-J":"0.839","CC":"0.651","FPS":"4.18","KLDiv":"0.593","NSS":"1.71","SIM":"0.586"},"uses_additional_data":false,"paper_date":"2018-01-23","paper":"/paper/revisiting-video-saliency-a-large-scale","paper_url":"http://arxiv.org/abs/1801.07424v3","paper_title":"Revisiting Video Saliency: A Large-scale Benchmark and a New Model","code":"https://github.com/wenguanwang/DHF1K","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"SalEMA","metrics":{"AUC-J":"0.821","CC":"0.636","FPS":"32.97","KLDiv":"0.647","NSS":"1.63","SIM":"0.571"},"uses_additional_data":false,"paper_date":"2019-07-03","paper":"/paper/simple-vs-complex-temporal-recurrences-for","paper_url":"https://arxiv.org/abs/1907.01869v4","paper_title":"Simple vs complex temporal recurrences for video saliency prediction","code":"https://github.com/Linardos/SalEMA","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"GASP","metrics":{"AUC-J":"0.810","CC":"0.613","FPS":"3.77","KLDiv":"0.687","NSS":"1.57","SIM":"0.557"},"uses_additional_data":false,"paper_date":"2022-06-09","paper":"/paper/gasp-gated-attention-for-saliency-prediction-1","paper_url":"https://arxiv.org/abs/2206.04590v1","paper_title":"GASP: Gated Attention For Saliency Prediction","code":"https://github.com/knowledgetechnologyuhh/gasp","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"HFT","metrics":{"AUC-J":"0.814","CC":"0.577","FPS":"3.63","KLDiv":"0.698","NSS":"1.35","SIM":"0.550"},"uses_additional_data":false,"paper_date":"2016-05-06","paper":"/paper/visual-saliency-based-on-scale-space-analysis","paper_url":"http://arxiv.org/abs/1605.01999v1","paper_title":"Visual Saliency Based on Scale-Space Analysis in the Frequency Domain","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"DeepVS","metrics":{"AUC-J":"0.804","CC":"0.586","FPS":"3.29","KLDiv":"0.707","NSS":"1.44","SIM":"0.548"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/deepvs-a-deep-learning-based-video-saliency","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Lai_Jiang_DeepVS_A_Deep_ECCV_2018_paper.html","paper_title":"DeepVS: A Deep Learning Based Video Saliency Prediction Approach","code":"https://github.com/remega/OMCNN_2CLSTM","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"GBVS","metrics":{"AUC-J":"0.810","CC":"0.572","FPS":"1.93","KLDiv":"0.709","NSS":"1.33","SIM":"0.546"},"uses_additional_data":false,"paper_date":"2006-12-04","paper":"/paper/graph-based-visual-saliency","paper_url":"https://proceedings.neurips.cc/paper_files/paper/2006/hash/4db0f8b0fc895da263fd77fc8aecabe4-Abstract.html","paper_title":"Graph-Based Visual Saliency","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"ITTI","metrics":{"AUC-J":"0.811","CC":"0.572","FPS":"2.23","KLDiv":"0.799","NSS":"1.34","SIM":"0.544"},"uses_additional_data":false,"paper_date":"1998-11-01","paper":"/paper/a-model-of-saliency-based-visual-attention","paper_url":"https://ieeexplore.ieee.org/abstract/document/730558","paper_title":"A model of saliency-based visual attention for rapid scene analysis","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 6,885 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":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"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":3,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":11,"n_unverified":6,"n_samples":17,"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":11,"n_unverified":6,"n_samples":17,"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"}}}