{"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/a-generative-approach-for-wikipedia-scale","title":"A Generative Approach for Wikipedia-Scale Visual Entity Recognition","arxiv_id":"2403.02041","date":"2024-03-04","proceeding":"CVPR 2024 1","authors":["Mathilde Caron","Ahmet Iscen","Alireza Fathi","Cordelia Schmid"],"abstract":"In this paper, we address web-scale visual entity recognition, specifically the task of mapping a given query image to one of the 6 million existing entities in Wikipedia. One way of approaching a problem of such scale is using dual-encoder models (eg CLIP), where all the entity names and query images are embedded into a unified space, paving the way for an approximate k-NN search. Alternatively, it is also possible to re-purpose a captioning model to directly generate the entity names for a given image. In contrast, we introduce a novel Generative Entity Recognition (GER) framework, which given an input image learns to auto-regressively decode a semantic and discriminative ``code'' identifying the target entity. Our experiments demonstrate the efficacy of this GER paradigm, showcasing state-of-the-art performance on the challenging OVEN benchmark. GER surpasses strong captioning, dual-encoder, visual matching and hierarchical classification baselines, affirming its advantage in tackling the complexities of web-scale recognition.","url_abs":"https://arxiv.org/abs/2403.02041v2","url_pdf":"https://arxiv.org/pdf/2403.02041v2.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":"a-generative-approach-for-wikipedia-scale","repo_url":"https://github.com/google-research/scenic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"a-generative-approach-for-wikipedia-scale","repo_url":"https://github.com/google-research/scenic/tree/main/scenic/projects/gerald","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[],"methods":[{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"ger","method_name":"GER"},{"method_slug":"k-nn","method_name":"k-NN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.02041","atlas_url":"https://app.syntology.ai/?focus=2403.02041","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}