{"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/scaling-egocentric-vision-the-epic-kitchens","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","arxiv_id":"1804.02748","date":"2018-04-08","proceeding":"ECCV 2018 9","authors":["Dima Damen","Hazel Doughty","Giovanni Maria Farinella","Sanja Fidler","Antonino Furnari","Evangelos Kazakos","Davide Moltisanti","Jonathan Munro","Toby Perrett","Will Price","Michael Wray"],"abstract":"First-person vision is gaining interest as it offers a unique viewpoint on\npeople's interaction with objects, their attention, and even intention.\nHowever, progress in this challenging domain has been relatively slow due to\nthe lack of sufficiently large datasets. In this paper, we introduce\nEPIC-KITCHENS, a large-scale egocentric video benchmark recorded by 32\nparticipants in their native kitchen environments. Our videos depict\nnonscripted daily activities: we simply asked each participant to start\nrecording every time they entered their kitchen. Recording took place in 4\ncities (in North America and Europe) by participants belonging to 10 different\nnationalities, resulting in highly diverse cooking styles. Our dataset features\n55 hours of video consisting of 11.5M frames, which we densely labeled for a\ntotal of 39.6K action segments and 454.3K object bounding boxes. Our annotation\nis unique in that we had the participants narrate their own videos (after\nrecording), thus reflecting true intention, and we crowd-sourced ground-truths\nbased on these. We describe our object, action and anticipation challenges, and\nevaluate several baselines over two test splits, seen and unseen kitchens.\nDataset and Project page: http://epic-kitchens.github.io","url_abs":"http://arxiv.org/abs/1804.02748v2","url_pdf":"http://arxiv.org/pdf/1804.02748v2.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":"scaling-egocentric-vision-the-epic-kitchens","repo_url":"https://github.com/epic-kitchens/annotations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"scaling-egocentric-vision-the-epic-kitchens","repo_url":"https://github.com/epic-kitchens/epic-kitchens-55-annotations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"action-anticipation","task_name":"Action Anticipation"}],"methods":[],"datasets_introduced":[{"slug":"epic-kitchens","name":"EPIC-KITCHENS-55","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-55-seen","task":"Action Anticipation","dataset":"EPIC-KITCHENS-55 (Seen test set (S1))","model":"ATSN","rank_in_archive_order":6,"of":7,"metrics":{"Top 1 Accuracy - Act.":"6.00","Top 1 Accuracy - Noun":"16.22","Top 1 Accuracy - Verb":"31.81","Top 5 Accuracy - Act.":"28.21","Top 5 Accuracy - Noun":"42.15","Top 5 Accuracy - Verb":"76.56"},"uses_additional_data":false},{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-55-seen","task":"Action Anticipation","dataset":"EPIC-KITCHENS-55 (Seen test set (S1))","model":"2SCNN","rank_in_archive_order":7,"of":7,"metrics":{"Top 1 Accuracy - Act.":"4.32","Top 1 Accuracy - Noun":"15.15","Top 1 Accuracy - Verb":"29.76","Top 5 Accuracy - Act.":"15.21","Top 5 Accuracy - Noun":"38.56","Top 5 Accuracy - Verb":"76.03"},"uses_additional_data":false},{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-55-1","task":"Action Anticipation","dataset":"EPIC-KITCHENS-55 (Unseen test set (S2)","model":"ATSN","rank_in_archive_order":6,"of":7,"metrics":{"Top 1 Accuracy - Act.":"2.39","Top 1 Accuracy - Noun":"10.41","Top 1 Accuracy - Verb":"25.30","Top 5 Accuracy - Act.":"6.63","Top 5 Accuracy - Noun":"29.50","Top 5 Accuracy - Verb":"68.32"},"uses_additional_data":false},{"leaderboard":"/sota/action-anticipation-on-epic-kitchens-55-1","task":"Action Anticipation","dataset":"EPIC-KITCHENS-55 (Unseen test set (S2)","model":"2SCNN","rank_in_archive_order":7,"of":7,"metrics":{"Top 1 Accuracy - Act.":"2.29","Top 1 Accuracy - Noun":"9.97","Top 1 Accuracy - Verb":"25.23","Top 5 Accuracy - Act.":"9.35","Top 5 Accuracy - Noun":"27.38","Top 5 Accuracy - Verb":"68.66"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.02748","atlas_url":"https://app.syntology.ai/?focus=1804.02748","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}