{"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-prediction","name":"Video Saliency Prediction","slug":"video-saliency-prediction","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":29,"papers_with_code":15,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0},"benchmarks":[],"datasets":[{"url":"/dataset/dhf1k","name":"DHF1K","full_name":"","num_papers_in_archive":24},{"url":"/dataset/avimos","name":"AViMoS","full_name":"Audio-Visual Mouse Saliency","num_papers_in_archive":1},{"url":"/dataset/egomon","name":"EgoMon","full_name":"Egomon Gaze & Video dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":29,"of":29,"of_with_code":15,"tagged_in_all":29,"counts":{"archive_papers_tagged":29,"with_a_code_link":15,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":29,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"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/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/dave-a-deep-audio-visual-embedding-for","slug":"dave-a-deep-audio-visual-embedding-for","title":"DAVE: A Deep Audio-Visual Embedding for Dynamic Saliency Prediction","date":"2019-05-25","arxiv_id":"1905.10693","repositories_listed":2,"syntology":null},{"url":"/paper/temporal-saliency-adaptation-in-egocentric","slug":"temporal-saliency-adaptation-in-egocentric","title":"Temporal Saliency Adaptation in Egocentric Videos","date":"2018-08-28","arxiv_id":"1808.09559","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/spherical-vision-transformer-for-360-degree","slug":"spherical-vision-transformer-for-360-degree","title":"Spherical Vision Transformer for 360-degree Video Saliency Prediction","date":"2023-08-24","arxiv_id":"2308.13004","repositories_listed":1,"syntology":null},{"url":"/paper/tinyhd-efficient-video-saliency-prediction","slug":"tinyhd-efficient-video-saliency-prediction","title":"TinyHD: Efficient Video Saliency Prediction with Heterogeneous Decoders using Hierarchical Maps Distillation","date":"2023-01-11","arxiv_id":"2301.04619","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/spatio-temporal-self-attention-network-for","slug":"spatio-temporal-self-attention-network-for","title":"Spatio-Temporal Self-Attention Network for Video Saliency Prediction","date":"2021-08-24","arxiv_id":"2108.10696","repositories_listed":1,"syntology":null},{"url":"/paper/noise-aware-saliency-prediction-for-videos","slug":"noise-aware-saliency-prediction-for-videos","title":"Noise-Aware Video Saliency Prediction","date":"2021-04-16","arxiv_id":"2104.08038","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/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/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/a-learning-based-visual-saliency-prediction","slug":"a-learning-based-visual-saliency-prediction","title":"A Learning-Based Visual Saliency Prediction Model for Stereoscopic 3D Video (LBVS-3D)","date":"2018-03-13","arxiv_id":"1803.04842","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-video-saliency-with-object-to","slug":"predicting-video-saliency-with-object-to","title":"Predicting Video Saliency with Object-to-Motion CNN and Two-layer Convolutional LSTM","date":"2017-09-19","arxiv_id":"1709.06316","repositories_listed":1,"syntology":null},{"url":null,"slug":"text-audio-visual-conditioned-diffusion-model","title":"Text-Audio-Visual-conditioned Diffusion Model for Video Saliency Prediction","date":"2025-04-19","arxiv_id":"2504.14267","repositories_listed":0,"syntology":null},{"url":null,"slug":"dtfsal-audio-visual-dynamic-token-fusion-for","title":"DTFSal: Audio-Visual Dynamic Token Fusion for Video Saliency Prediction","date":"2025-04-14","arxiv_id":"2504.10070","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimalistic-video-saliency-prediction-via","title":"Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues","date":"2025-02-01","arxiv_id":"2502.00397","repositories_listed":0,"syntology":null},{"url":null,"slug":"relevance-guided-audio-visual-fusion-for","title":"Relevance-guided Audio Visual Fusion for Video Saliency Prediction","date":"2024-11-18","arxiv_id":"2411.11454","repositories_listed":0,"syntology":null},{"url":null,"slug":"cardiff-video-salient-object-ranking-chain-of","title":"CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion","date":"2024-08-21","arxiv_id":"2408.12009","repositories_listed":0,"syntology":null},{"url":null,"slug":"salfom-dynamic-saliency-prediction-with-video","title":"SalFoM: Dynamic Saliency Prediction with Video Foundation Models","date":"2024-04-03","arxiv_id":"2404.03097","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-video-saliency-prediction","title":"Transformer-based Video Saliency Prediction with High Temporal Dimension Decoding","date":"2024-01-15","arxiv_id":"2401.07942","repositories_listed":0,"syntology":null},{"url":null,"slug":"unist-towards-unifying-saliency-transformer","title":"UniST: Towards Unifying Saliency Transformer for Video Saliency Prediction and Detection","date":"2023-09-15","arxiv_id":"2309.08220","repositories_listed":0,"syntology":null},{"url":null,"slug":"casp-net-rethinking-video-saliency-prediction","title":"CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspective","date":"2023-03-11","arxiv_id":"2303.06357","repositories_listed":0,"syntology":null},{"url":null,"slug":"casp-net-rethinking-video-saliency-prediction-1","title":"CASP-Net: Rethinking Video Saliency Prediction From an Audio-Visual Consistency Perceptual Perspective","date":"2023-01-01","arxiv_id":null,"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":"how-drones-look-crowdsourced-knowledge","title":"Model-guided Multi-path Knowledge Aggregation for Aerial Saliency Prediction","date":"2018-11-14","arxiv_id":"1811.05625","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":"benchmark-3d-eye-tracking-dataset-for-visual","title":"Benchmark 3D eye-tracking dataset for visual saliency prediction on stereoscopic 3D video","date":"2018-03-13","arxiv_id":"1803.04845","repositories_listed":0,"syntology":null}],"syntology_records":0,"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":0,"papers_where_code_ran_first_page":null,"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":[],"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":"8893dda386c67e1457614a2a69359dc41d52f72dd23d4c9e6d5cddf118bac546","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}