{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/tempsal-uncovering-temporal-information-for-1","title":"TempSAL - Uncovering Temporal Information for Deep Saliency Prediction","arxiv_id":null,"date":"2023-01-01","proceeding":"CVPR 2023 1","authors":["Bahar Aydemir","Ludo Hoffstetter","Tong Zhang","Mathieu Salzmann","Sabine Süsstrunk"],"abstract":"    Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information such as scene context, semantic relationships, gaze direction, and object dissimilarity. However, none of these models consider the temporal nature of gaze shifts during image observation. We introduce a novel saliency prediction model that learns to output saliency maps in sequential time intervals by exploiting human temporal attention patterns. Our approach locally modulates the saliency predictions by combining the learned temporal maps. Our experiments show that our method outperforms the state-of-the-art models, including a multi-duration saliency model, on the SALICON benchmark and CodeCharts1k dataset. Our code is publicly available on GitHub.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2023/html/Aydemir_TempSAL_-_Uncovering_Temporal_Information_for_Deep_Saliency_Prediction_CVPR_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2023/papers/Aydemir_TempSAL_-_Uncovering_Temporal_Information_for_Deep_Saliency_Prediction_CVPR_2023_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tempsal-uncovering-temporal-information-for-1","repo_url":"https://github.com/IVRL/Tempsal","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"saliency-prediction","task_name":"Saliency Prediction"}],"methods":[{"method_slug":null,"method_name":"None"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/saliency-prediction-on-saleci","task":"Saliency Prediction","dataset":"SALECI","model":"TempSAL","rank_in_archive_order":4,"of":5,"metrics":{"KL":"0.712"},"uses_additional_data":false},{"leaderboard":"/sota/saliency-prediction-on-salicon","task":"Saliency Prediction","dataset":"SALICON","model":"TempSAL","rank_in_archive_order":3,"of":5,"metrics":{"AUC":"0.869","CC":"0.911","KLD":"0.195","NSS":"1.967","SIM":"0.800","sAUC":"0.745"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}