{"url":"/task/saliency-prediction","name":"Saliency Prediction","slug":"saliency-prediction","description_markdown":"A saliency map is a model that predicts eye fixations on a visual scene. Saliency prediction is informed by the human visual attention mechanism and predicts the possibility of the human eyes to stay in a certain position in the scene.","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":268,"papers_with_code":105,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":9,"subtasks":2,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/saliency-prediction-on-saleci","slug":"saliency-prediction-on-saleci","dataset":"SALECI","dataset_url":null,"rows_in_archive":5,"metrics":["KL"],"first_row_in_archive_order":{"model":"SUM","paper_title":"SUM: Saliency Unification through Mamba for Visual Attention Modeling","paper_url":"/paper/sum-saliency-unification-through-mamba-for","paper_date":"2024-06-25","arxiv_id":"2406.17815","code_links":[{"title":"Arhosseini77/SUM","url":"https://github.com/Arhosseini77/SUM"}],"syntology":{"n":14,"n_ran":14,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/saliency-prediction-on-salicon","slug":"saliency-prediction-on-salicon","dataset":"SALICON","dataset_url":"/dataset/salicon","rows_in_archive":5,"metrics":["AUC","CC","KLD","NSS","SIM","sAUC","IG"],"first_row_in_archive_order":{"model":"SUM","paper_title":"SUM: Saliency Unification through Mamba for Visual Attention Modeling","paper_url":"/paper/sum-saliency-unification-through-mamba-for","paper_date":"2024-06-25","arxiv_id":"2406.17815","code_links":[{"title":"Arhosseini77/SUM","url":"https://github.com/Arhosseini77/SUM"}],"syntology":{"n":14,"n_ran":14,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/saliency-prediction-on-mit300","slug":"saliency-prediction-on-mit300","dataset":"MIT300","dataset_url":null,"rows_in_archive":2,"metrics":["AUC-Judd","CC","KLD","NSS","SIM","sAUC"],"first_row_in_archive_order":{"model":"SUM","paper_title":"SUM: Saliency Unification through Mamba for Visual Attention Modeling","paper_url":"/paper/sum-saliency-unification-through-mamba-for","paper_date":"2024-06-25","arxiv_id":"2406.17815","code_links":[{"title":"Arhosseini77/SUM","url":"https://github.com/Arhosseini77/SUM"}],"syntology":{"n":14,"n_ran":14,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/saliency-prediction-on-cat2000","slug":"saliency-prediction-on-cat2000","dataset":"CAT2000","dataset_url":"/dataset/cat2000","rows_in_archive":1,"metrics":["KL"],"first_row_in_archive_order":{"model":"SUM","paper_title":"SUM: Saliency Unification through Mamba for Visual Attention Modeling","paper_url":"/paper/sum-saliency-unification-through-mamba-for","paper_date":"2024-06-25","arxiv_id":"2406.17815","code_links":[{"title":"Arhosseini77/SUM","url":"https://github.com/Arhosseini77/SUM"}],"syntology":{"n":14,"n_ran":14,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/salicon","name":"SALICON","full_name":"Salicency in Context","num_papers_in_archive":161},{"url":"/dataset/isun","name":"iSUN","full_name":"iSUN","num_papers_in_archive":108},{"url":"/dataset/uieb","name":"UIEB","full_name":"Underwater Image Enhancement Benchmark Dataset","num_papers_in_archive":87},{"url":"/dataset/cat2000","name":"CAT2000","full_name":"","num_papers_in_archive":57},{"url":"/dataset/suim","name":"SUIM","full_name":"Segmentation of Underwater IMagery","num_papers_in_archive":34},{"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},{"url":"/dataset/capmit1003","name":"CapMIT1003","full_name":"","num_papers_in_archive":1},{"url":"/dataset/salient-kitti","name":"Salient-KITTI","full_name":null,"num_papers_in_archive":1}],"subtasks":[{"url":"/task/aerial-video-saliency-prediction","name":"Aerial Video Saliency Prediction"},{"url":"/task/saliency-prediction-1","name":"Few-Shot Transfer Learning for Saliency Prediction"}],"parent_tasks":[{"url":"/task/saliency-detection","name":"Saliency Detection"},{"url":"/task/saliency-prediction-1","name":"Few-Shot Transfer Learning for Saliency Prediction"}],"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":30,"of":105,"tagged_in_all":268,"items":[{"url":"/paper/uncertainty-inspired-rgb-d-saliency-detection","title":"Uncertainty Inspired RGB-D Saliency Detection","date":"2020-09-07","arxiv_id":"2009.03075","repositories_listed":4,"syntology":null},{"url":"/paper/simultaneous-enhancement-and-super-resolution","title":"Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception","date":"2020-02-04","arxiv_id":"2002.01155","repositories_listed":4,"syntology":null},{"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/salgan-visual-saliency-prediction-with","title":"SalGAN: Visual Saliency Prediction with Generative Adversarial Networks","date":"2017-01-04","arxiv_id":"1701.01081","repositories_listed":4,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/specificity-preserving-rgb-d-saliency","title":"Specificity-preserving RGB-D Saliency Detection","date":"2021-08-18","arxiv_id":"2108.08162","repositories_listed":3,"syntology":{"n":14,"n_ran":8,"n_unverified":6,"n_pointer_only":14}},{"url":"/paper/semantic-segmentation-of-underwater-imagery","title":"Semantic Segmentation of Underwater Imagery: Dataset and Benchmark","date":"2020-04-02","arxiv_id":"2004.01241","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/basnet-boundary-aware-salient-object","title":"BASNet: Boundary-Aware Salient Object Detection","date":"2019-06-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/fast-underwater-image-enhancement-for","title":"Fast Underwater Image Enhancement for Improved Visual Perception","date":"2019-03-23","arxiv_id":"1903.09766","repositories_listed":3,"syntology":null},{"url":"/paper/reverse-attention-for-salient-object","title":"Reverse Attention for Salient Object Detection","date":"2018-07-26","arxiv_id":"1807.09940","repositories_listed":3,"syntology":null},{"url":"/paper/calibrated-prediction-in-and-out-of-domain","title":"DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling","date":"2021-05-26","arxiv_id":"2105.12441","repositories_listed":2,"syntology":{"n":20,"n_ran":13,"n_unverified":7,"n_pointer_only":16}},{"url":"/paper/transformer-transforms-salient-object","title":"Generative Transformer for Accurate and Reliable Salient Object Detection","date":"2021-04-20","arxiv_id":"2104.10127","repositories_listed":2,"syntology":null},{"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/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/picanet-pixel-wise-contextual-attention","title":"PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection","date":"2018-12-15","arxiv_id":"1812.06314","repositories_listed":2,"syntology":null},{"url":"/paper/a-neurodynamic-model-of-saliency-prediction","title":"A Neurodynamic model of Saliency prediction in V1","date":"2018-11-15","arxiv_id":"1811.06308","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/understanding-humans-in-crowded-scenes-deep","title":"Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing","date":"2018-04-10","arxiv_id":"1804.03287","repositories_listed":2,"syntology":null},{"url":"/paper/predicting-gaze-in-egocentric-video-by","title":"Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition","date":"2018-03-24","arxiv_id":"1803.09125","repositories_listed":2,"syntology":null},{"url":"/paper/faster-gaze-prediction-with-dense-networks","title":"Faster gaze prediction with dense networks and Fisher pruning","date":"2018-01-17","arxiv_id":"1801.05787","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/beyond-saliency-understanding-convolutional","title":"Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation","date":"2017-12-22","arxiv_id":"1712.08268","repositories_listed":2,"syntology":null},{"url":"/paper/predicting-human-eye-fixations-via-an-lstm","title":"Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model","date":"2016-11-29","arxiv_id":"1611.09571","repositories_listed":2,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/a-deep-multi-level-network-for-saliency","title":"A Deep Multi-Level Network for Saliency Prediction","date":"2016-09-05","arxiv_id":"1609.01064","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/case-contrastive-activation-for-saliency","title":"CASE: Contrastive Activation for Saliency Estimation","date":"2025-06-08","arxiv_id":"2506.07327","repositories_listed":1,"syntology":null},{"url":"/paper/cspenet-contour-aware-and-saliency-priors","title":"CSPENet: Contour-Aware and Saliency Priors Embedding Network for Infrared Small Target Detection","date":"2025-05-15","arxiv_id":"2505.09943","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-guided-refinement-for-fine","title":"Uncertainty Guided Refinement for Fine-Grained Salient Object Detection","date":"2025-04-13","arxiv_id":"2504.09666","repositories_listed":1,"syntology":null},{"url":"/paper/mesh-mamba-a-unified-state-space-model-for","title":"Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes","date":"2025-04-02","arxiv_id":"2504.01466","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-learning-framework-for-visual","title":"A Deep Learning Framework for Visual Attention Prediction and Analysis of News Interfaces","date":"2025-03-21","arxiv_id":"2503.17212","repositories_listed":1,"syntology":null},{"url":"/paper/textured-mesh-saliency-bridging-geometry-and","title":"Textured Mesh Saliency: Bridging Geometry and Texture for Human Perception in 3D Graphics","date":"2024-12-11","arxiv_id":"2412.08188","repositories_listed":1,"syntology":null},{"url":"/paper/correlation-of-object-detection-performance","title":"Correlation of Object Detection Performance with Visual Saliency and Depth Estimation","date":"2024-11-05","arxiv_id":"2411.02844","repositories_listed":1,"syntology":null}],"syntology_records":9,"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"}}