{"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-large-scale-dataset-and-benchmark-for","title":"A Large-scale Dataset and Benchmark for Similar Trademark Retrieval","arxiv_id":"1701.05766","date":"2017-01-20","proceeding":null,"authors":["Osman Tursun","Cemal Aker","Sinan Kalkan"],"abstract":"Trademark retrieval (TR) has become an important yet challenging problem due\nto an ever increasing trend in trademark applications and infringement\nincidents. There have been many promising attempts for the TR problem, which,\nhowever, fell impracticable since they were evaluated with limited and mostly\ntrivial datasets. In this paper, we provide a large-scale dataset with\nbenchmark queries with which different TR approaches can be evaluated\nsystematically. Moreover, we provide a baseline on this benchmark using the\nwidely-used methods applied to TR in the literature. Furthermore, we identify\nand correct two important issues in TR approaches that were not addressed\nbefore: reversal of contrast, and presence of irrelevant text in trademarks\nseverely affect the TR methods. Lastly, we applied deep learning, namely,\nseveral popular Convolutional Neural Network models, to the TR problem. To the\nbest of the authors, this is the first attempt to do so.","url_abs":"http://arxiv.org/abs/1701.05766v2","url_pdf":"http://arxiv.org/pdf/1701.05766v2.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-large-scale-dataset-and-benchmark-for","repo_url":"https://github.com/neouyghur/METU-TRADEMARK-DATASET","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-large-scale-dataset-and-benchmark-for","repo_url":"https://github.com/neouyghur/METU_TRADEMARK_DATASET","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"trademark-retrieval","task_name":"Trademark Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"metu-trademark-dataset","name":"METU Trademark","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}