{"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 (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":15,"of":15,"tagged_in_all":29,"items":[{"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/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","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","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","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","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","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","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","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","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/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","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","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","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}],"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"},"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"}}