{"url":"/task/multi-modal-document-classification","name":"Multi-Modal Document Classification","slug":"multi-modal-document-classification","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4,"papers_with_code":4,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":6,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/food-101","name":"Food-101","full_name":"","num_papers_in_archive":805},{"url":"/dataset/rvl-cdip","name":"RVL-CDIP","full_name":"RVL-CDIP","num_papers_in_archive":107},{"url":"/dataset/reuters-21578","name":"Reuters-21578","full_name":"","num_papers_in_archive":66},{"url":"/dataset/tobacco-3482","name":"Tobacco-3482","full_name":"","num_papers_in_archive":5},{"url":"/dataset/herigraph","name":"HeriGraph","full_name":"Multimodal Machine Learning Datasets on Graphs of Heritage Values and Attributes","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":4,"of":4,"tagged_in_all":4,"items":[{"url":"/paper/are-these-birds-similar-learning-branched","title":"Are These Birds Similar: Learning Branched Networks for Fine-grained Representations","date":"2020-01-16","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/message-passing-attention-networks-for","title":"Message Passing Attention Networks for Document Understanding","date":"2019-08-17","arxiv_id":"1908.06267","repositories_listed":2,"syntology":null},{"url":"/paper/image-and-text-fusion-for-upmc-food-101-using","title":"Image and Text fusion for UPMC Food-101 \\\\using BERT and CNNs","date":"2020-12-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-accuracy-and-speeding-up-document","title":"Improving accuracy and speeding up Document Image Classification through parallel systems","date":"2020-06-16","arxiv_id":"2006.09141","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}