{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":21,"of":21,"tagged_in_all":36,"items":[{"url":"/paper/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":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/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":3,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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_unverified":2,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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","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","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","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","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","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_unverified":2,"n_pointer_only":0}},{"url":"/paper/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","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","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}],"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}