{"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/cat2000-a-large-scale-fixation-dataset-for","title":"CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research","arxiv_id":"1505.03581","date":"2015-05-14","proceeding":null,"authors":["Ali Borji","Laurent Itti"],"abstract":"Saliency modeling has been an active research area in computer vision for\nabout two decades. Existing state of the art models perform very well in\npredicting where people look in natural scenes. There is, however, the risk\nthat these models may have been overfitting themselves to available small scale\nbiased datasets, thus trapping the progress in a local minimum. To gain a\ndeeper insight regarding current issues in saliency modeling and to better\ngauge progress, we recorded eye movements of 120 observers while they freely\nviewed a large number of naturalistic and artificial images. Our stimuli\nincludes 4000 images; 200 from each of 20 categories covering different types\nof scenes such as Cartoons, Art, Objects, Low resolution images, Indoor,\nOutdoor, Jumbled, Random, and Line drawings. We analyze some basic properties\nof this dataset and compare some successful models. We believe that our dataset\nopens new challenges for the next generation of saliency models and helps\nconduct behavioral studies on bottom-up visual attention.","url_abs":"http://arxiv.org/abs/1505.03581v1","url_pdf":"http://arxiv.org/pdf/1505.03581v1.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":"cat2000-a-large-scale-fixation-dataset-for","repo_url":"https://github.com/rAm1n/SEQUAL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"cat2000-a-large-scale-fixation-dataset-for","repo_url":"https://github.com/rAm1n/saliency","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"cat2000","name":"CAT2000","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1505.03581","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}