{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/video-saliency-detection","name":"Video Saliency Detection","slug":"video-saliency-detection","description_markdown":"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.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":36,"papers_with_code":21,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-saliency-detection-on-msu-video","slug":"video-saliency-detection-on-msu-video","dataset":"MSU Video Saliency Prediction","dataset_url":"/dataset/msu-video-saliency-prediction","rows_in_archive":14,"metrics":["SIM","CC","NSS","AUC-J","KLDiv","FPS"],"first_row_in_archive_order":{"model":"ViNet (dave)","paper_title":"ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction","paper_url":"/paper/avinet-diving-deep-into-audio-visual-saliency","paper_date":"2020-12-11","arxiv_id":"2012.06170","code_links":[{"title":"samyak0210/ViNet","url":"https://github.com/samyak0210/ViNet"}],"syntology":null}},{"leaderboard":"/sota/video-saliency-detection-on-dhf1k","slug":"video-saliency-detection-on-dhf1k","dataset":"DHF1K","dataset_url":"/dataset/dhf1k","rows_in_archive":3,"metrics":["NSS","AUC-J","CC","s-AUC","SIM"],"first_row_in_archive_order":{"model":"ViNet","paper_title":"ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction","paper_url":"/paper/avinet-diving-deep-into-audio-visual-saliency","paper_date":"2020-12-11","arxiv_id":"2012.06170","code_links":[{"title":"samyak0210/ViNet","url":"https://github.com/samyak0210/ViNet"}],"syntology":null}},{"leaderboard":"/sota/video-saliency-detection-on-diem","slug":"video-saliency-detection-on-diem","dataset":"DIEM","dataset_url":null,"rows_in_archive":1,"metrics":["CC"],"first_row_in_archive_order":{"model":"AViNet","paper_title":"ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction","paper_url":"/paper/avinet-diving-deep-into-audio-visual-saliency","paper_date":"2020-12-11","arxiv_id":"2012.06170","code_links":[{"title":"samyak0210/ViNet","url":"https://github.com/samyak0210/ViNet"}],"syntology":null}},{"leaderboard":"/sota/video-saliency-detection-on-hollywood2","slug":"video-saliency-detection-on-hollywood2","dataset":"Hollywood2","dataset_url":null,"rows_in_archive":1,"metrics":["CC"],"first_row_in_archive_order":{"model":"ViNet","paper_title":"ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction","paper_url":"/paper/avinet-diving-deep-into-audio-visual-saliency","paper_date":"2020-12-11","arxiv_id":"2012.06170","code_links":[{"title":"samyak0210/ViNet","url":"https://github.com/samyak0210/ViNet"}],"syntology":null}},{"leaderboard":"/sota/video-saliency-detection-on-ucfsports","slug":"video-saliency-detection-on-ucfsports","dataset":"UCFSports","dataset_url":null,"rows_in_archive":1,"metrics":["CC"],"first_row_in_archive_order":{"model":"ViNet","paper_title":"ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction","paper_url":"/paper/avinet-diving-deep-into-audio-visual-saliency","paper_date":"2020-12-11","arxiv_id":"2012.06170","code_links":[{"title":"samyak0210/ViNet","url":"https://github.com/samyak0210/ViNet"}],"syntology":null}}],"datasets":[{"url":"/dataset/dhf1k","name":"DHF1K","full_name":"","num_papers_in_archive":24},{"url":"/dataset/msu-video-saliency-prediction","name":"MSU Video Saliency Prediction","full_name":"","num_papers_in_archive":14},{"url":"/dataset/avimos","name":"AViMoS","full_name":"Audio-Visual Mouse Saliency","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/saliency-detection","name":"Saliency Detection"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":36,"of":36,"of_with_code":21,"tagged_in_all":36,"counts":{"archive_papers_tagged":36,"with_a_code_link":21,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":36,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/contextual-encoder-decoder-network-for-visual","slug":"contextual-encoder-decoder-network-for-visual","title":"Contextual Encoder-Decoder Network for Visual Saliency Prediction","date":"2019-02-18","arxiv_id":"1902.06634","repositories_listed":4,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/contextual-encoder-decoder-network-for-visual#ran","syntology_url":"https://syntology.ai/paper/1902.06634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.06634"}},"official":{"repos":["alexanderkroner/saliency"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/unified-image-and-video-saliency-modeling","slug":"unified-image-and-video-saliency-modeling","title":"Unified Image and Video Saliency Modeling","date":"2020-03-11","arxiv_id":"2003.05477","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unified-image-and-video-saliency-modeling#ran","syntology_url":"https://syntology.ai/paper/2003.05477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05477"}},"official":{"repos":["rdroste/unisal"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/simple-vs-complex-temporal-recurrences-for","slug":"simple-vs-complex-temporal-recurrences-for","title":"Simple vs complex temporal recurrences for video saliency prediction","date":"2019-07-03","arxiv_id":"1907.01869","repositories_listed":2,"syntology":null},{"url":"/paper/aim-2024-challenge-on-video-saliency","slug":"aim-2024-challenge-on-video-saliency","title":"AIM 2024 Challenge on Video Saliency Prediction: Methods and Results","date":"2024-09-23","arxiv_id":"2409.14827","repositories_listed":1,"syntology":null},{"url":"/paper/vidsod-100-a-new-dataset-and-a-baseline-model","slug":"vidsod-100-a-new-dataset-and-a-baseline-model","title":"ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection","date":"2024-06-18","arxiv_id":"2406.12536","repositories_listed":1,"syntology":null},{"url":"/paper/an-integrated-system-for-spatio-temporal","slug":"an-integrated-system-for-spatio-temporal","title":"An Integrated System for Spatio-Temporal Summarization of 360-degrees Videos","date":"2023-12-05","arxiv_id":"2312.02576","repositories_listed":1,"syntology":null},{"url":"/paper/panoramic-vision-transformer-for-saliency","slug":"panoramic-vision-transformer-for-saliency","title":"Panoramic Vision Transformer for Saliency Detection in 360° Videos","date":"2022-09-19","arxiv_id":"2209.08956","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/panoramic-vision-transformer-for-saliency#ran","syntology_url":"https://syntology.ai/paper/2209.08956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.08956"}},"official":{"repos":["hs-yn/paver"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-comprehensive-survey-on-video-saliency","slug":"a-comprehensive-survey-on-video-saliency","title":"A Comprehensive Survey on Video Saliency Detection with Auditory Information: the Audio-visual Consistency Perceptual is the Key!","date":"2022-06-20","arxiv_id":"2206.13390","repositories_listed":1,"syntology":null},{"url":"/paper/gasp-gated-attention-for-saliency-prediction-1","slug":"gasp-gated-attention-for-saliency-prediction-1","title":"GASP: Gated Attention For Saliency Prediction","date":"2022-06-09","arxiv_id":"2206.04590","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-visual-auditory-saliency","slug":"weakly-supervised-visual-auditory-saliency","title":"Weakly Supervised Visual-Auditory Fixation Prediction with Multigranularity Perception","date":"2021-12-27","arxiv_id":"2112.13697","repositories_listed":1,"syntology":null},{"url":"/paper/from-semantic-categories-to-fixations-a-novel","slug":"from-semantic-categories-to-fixations-a-novel","title":"From Semantic Categories to Fixations: A Novel Weakly-Supervised Visual-Auditory Saliency Detection Approach","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-video-salient-object","slug":"weakly-supervised-video-salient-object","title":"Weakly Supervised Video Salient Object Detection","date":"2021-04-06","arxiv_id":"2104.02391","repositories_listed":1,"syntology":null},{"url":"/paper/avinet-diving-deep-into-audio-visual-saliency","slug":"avinet-diving-deep-into-audio-visual-saliency","title":"ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction","date":"2020-12-11","arxiv_id":"2012.06170","repositories_listed":1,"syntology":null},{"url":"/paper/video-saliency-detection-with-domain-adaption","slug":"video-saliency-detection-with-domain-adaption","title":"Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction","date":"2020-10-02","arxiv_id":"2010.01220","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-rich-and-efficient-spatial-temporal","slug":"exploring-rich-and-efficient-spatial-temporal","title":"Exploring Rich and Efficient Spatial Temporal Interactions for Real Time Video Salient Object Detection","date":"2020-08-07","arxiv_id":"2008.02973","repositories_listed":1,"syntology":null},{"url":"/paper/a-plug-and-play-scheme-to-adapt-image","slug":"a-plug-and-play-scheme-to-adapt-image","title":"A Plug-and-play Scheme to Adapt Image Saliency Deep Model for Video Data","date":"2020-08-02","arxiv_id":"2008.09103","repositories_listed":1,"syntology":null},{"url":"/paper/video-saliency-prediction-using-enhanced","slug":"video-saliency-prediction-using-enhanced","title":"Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network","date":"2020-01-02","arxiv_id":"2001.00292","repositories_listed":1,"syntology":null},{"url":"/paper/tased-net-temporally-aggregating-spatial","slug":"tased-net-temporally-aggregating-spatial","title":"TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection","date":"2019-08-15","arxiv_id":"1908.05786","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/tased-net-temporally-aggregating-spatial#ran","syntology_url":"https://syntology.ai/paper/1908.05786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.05786"}},"official":{"repos":["kylemin/TASED-Net"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/a-dilated-inception-network-for-visual","slug":"a-dilated-inception-network-for-visual","title":"A Dilated Inception Network for Visual Saliency Prediction","date":"2019-04-07","arxiv_id":"1904.03571","repositories_listed":1,"syntology":null},{"url":"/paper/deepvs-a-deep-learning-based-video-saliency","slug":"deepvs-a-deep-learning-based-video-saliency","title":"DeepVS: A Deep Learning Based Video Saliency Prediction Approach","date":"2018-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-video-saliency-a-large-scale","slug":"revisiting-video-saliency-a-large-scale","title":"Revisiting Video Saliency: A Large-scale Benchmark and a New Model","date":"2018-01-23","arxiv_id":"1801.07424","repositories_listed":1,"syntology":null},{"url":null,"slug":"saliency-detection-in-educational-videos","title":"Saliency Detection in Educational Videos: Analyzing the Performance of Current Models, Identifying Limitations and Advancement Directions","date":"2024-08-08","arxiv_id":"2408.04515","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-spatial-feature-pyramid-for-video","title":"Temporal-Spatial Feature Pyramid for Video Saliency Detection","date":"2021-05-10","arxiv_id":"2105.04213","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-explore-intrinsic-saliency-for","title":"Learning to Explore Intrinsic Saliency for Stereoscopic Video","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-uncertainty-estimation-using","title":"Unsupervised uncertainty estimation using spatiotemporal cues in video saliency detection","date":"2019-01-06","arxiv_id":"1901.01550","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-and-local-sensitivity-guided-key","title":"Global and Local Sensitivity Guided Key Salient Object Re-augmentation for Video Saliency Detection","date":"2018-11-19","arxiv_id":"1811.07480","repositories_listed":0,"syntology":null},{"url":null,"slug":"salient-object-detection-in-video-using-deep","title":"Salient Object Detection in Video using Deep Non-Local Neural Networks","date":"2018-10-16","arxiv_id":"1810.07097","repositories_listed":0,"syntology":null},{"url":null,"slug":"sg-fcn-a-motion-and-memory-based-deep","title":"SG-FCN: A Motion and Memory-Based Deep Learning Model for Video Saliency Detection","date":"2018-09-21","arxiv_id":"1809.07988","repositories_listed":0,"syntology":null},{"url":null,"slug":"saliency-detection-in-360a-videos","title":"Saliency Detection in 360Â° Videos","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-saliency-detection-by-3d-convolutional","title":"Video Saliency Detection by 3D Convolutional Neural Networks","date":"2018-07-12","arxiv_id":"1807.04514","repositories_listed":0,"syntology":null},{"url":null,"slug":"review-of-visual-saliency-detection-with","title":"Review of Visual Saliency Detection with Comprehensive Information","date":"2018-03-09","arxiv_id":"1803.03391","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-theoretic-spatiotemporal-context","title":"Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection","date":"2017-07-25","arxiv_id":"1707.07815","repositories_listed":0,"syntology":null},{"url":"/paper/visual-saliency-based-on-scale-space-analysis","slug":"visual-saliency-based-on-scale-space-analysis","title":"Visual Saliency Based on Scale-Space Analysis in the Frequency Domain","date":"2016-05-06","arxiv_id":"1605.01999","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoding-based-saliency-detection-for-videos","title":"Encoding Based Saliency Detection for Videos and Images","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/graph-based-visual-saliency","slug":"graph-based-visual-saliency","title":"Graph-Based Visual Saliency","date":"2006-12-04","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/a-model-of-saliency-based-visual-attention","slug":"a-model-of-saliency-based-visual-attention","title":"A model of saliency-based visual attention for rapid scene analysis","date":"1998-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/task/video-saliency-detection/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/video-saliency-detection/papers/ran/1","json":"/task/video-saliency-detection/papers/ran/1.json","rows":3}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"2cc6da83bf9c077a1beda19d3c9714bc924f7ffabd583f88a3d7ee0cca8ebfbe","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}