{"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/yfcc100m-the-new-data-in-multimedia-research","title":"YFCC100M: The New Data in Multimedia Research","arxiv_id":"1503.01817","date":"2015-03-05","proceeding":null,"authors":["Bart Thomee","David A. Shamma","Gerald Friedland","Benjamin Elizalde","Karl Ni","Douglas Poland","Damian Borth","Li-Jia Li"],"abstract":"We present the Yahoo Flickr Creative Commons 100 Million Dataset (YFCC100M), the largest public multimedia collection that has ever been released. The dataset contains a total of 100 million media objects, of which approximately 99.2 million are photos and 0.8 million are videos, all of which carry a Creative Commons license. Each media object in the dataset is represented by several pieces of metadata, e.g. Flickr identifier, owner name, camera, title, tags, geo, media source. The collection provides a comprehensive snapshot of how photos and videos were taken, described, and shared over the years, from the inception of Flickr in 2004 until early 2014. In this article we explain the rationale behind its creation, as well as the implications the dataset has for science, research, engineering, and development. We further present several new challenges in multimedia research that can now be expanded upon with our dataset.","url_abs":"http://arxiv.org/abs/1503.01817v2","url_pdf":"http://arxiv.org/pdf/1503.01817v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"yfcc100m-the-new-data-in-multimedia-research","repo_url":"https://github.com/cesc-park/attend2u","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"yfcc100m-the-new-data-in-multimedia-research","repo_url":"https://github.com/ctr4si/attend2u","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"yfcc100m","name":"YFCC100M","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1503.01817","atlas_url":"https://app.syntology.ai/?focus=1503.01817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1503.01817"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cesc-park/attend2u","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ctr4si/attend2u","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"listed":{"samples":4,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d6f215d655a876ee","entry":"my_lcs","repo":"cesc-park/attend2u","repo_kind":"listed","path":"utils/pycocoevalcap/rouge/rouge.py","file_url":"https://github.com/cesc-park/attend2u/blob/HEAD/utils/pycocoevalcap/rouge/rouge.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6f215d655a876ee"}},{"code_sha256_prefix":"5172aba957a32d9e","entry":"cook_refs","repo":"cesc-park/attend2u","repo_kind":"listed","path":"utils/pycocoevalcap/cider/cider_scorer.py","file_url":"https://github.com/cesc-park/attend2u/blob/HEAD/utils/pycocoevalcap/cider/cider_scorer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5172aba957a32d9e"}},{"code_sha256_prefix":"90a4bcbf05586ff3","entry":"cook_test","repo":"cesc-park/attend2u","repo_kind":"listed","path":"utils/pycocoevalcap/cider/cider_scorer.py","file_url":"https://github.com/cesc-park/attend2u/blob/HEAD/utils/pycocoevalcap/cider/cider_scorer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90a4bcbf05586ff3"}},{"code_sha256_prefix":"422c41f5b22cf9c3","entry":"precook","repo":"cesc-park/attend2u","repo_kind":"listed","path":"utils/pycocoevalcap/cider/cider_scorer.py","file_url":"https://github.com/cesc-park/attend2u/blob/HEAD/utils/pycocoevalcap/cider/cider_scorer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"422c41f5b22cf9c3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}