{"url":"/dataset/tobacco-3482","name":"Tobacco-3482","full_name":null,"description_markdown":"The Tobacco-3482 dataset consists of document images belonging to 10 classes such as letter, form, email, resume, memo, etc. The dataset has 3482 images.","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Document Text Classification","url":"/task/document-text-classification","datasets_with_task":"/datasets/task/document-text-classification"},{"name":"Document Image Classification","url":"/task/document-image-classification","datasets_with_task":"/datasets/task/document-image-classification"},{"name":"Multi-Modal Document Classification","url":"/task/multi-modal-document-classification","datasets_with_task":"/datasets/task/multi-modal-document-classification"}],"languages":[],"variants":["Tobacco-3482"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/document-image-classification-on-tobacco-3482","task":"Document Image Classification","dataset_variant":"Tobacco-3482","rows":10,"metrics":["Accuracy","Memory"],"first_row_in_archive_order":{"model":"DocXClassifier-L","paper":"/paper/docxclassifier-high-performance-explainable","metrics":{"Accuracy":"95.57"},"code_links":[{"title":"saifullah3396/docxclassifier","url":"https://github.com/saifullah3396/docxclassifier"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/document-text-classification-on-tobacco-3482","task":"Document Text Classification","dataset_variant":"Tobacco-3482","rows":3,"metrics":["Accuracy","Training time (hours)"],"first_row_in_archive_order":{"model":"Optimized Text CNN","paper":"/paper/light-weighted-cnn-for-text-classification","metrics":{"Accuracy":"46","Training time (hours)":"2"},"code_links":[{"title":"RituYadav92/Lightweighted-CNN-for-Document-Classification","url":"https://github.com/RituYadav92/Lightweighted-CNN-for-Document-Classification"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/multimodal-side-tuning-for-document","title":"Multimodal Side-Tuning for Document Classification","date":"2023-01-16","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/docxclassifier-high-performance-explainable","title":"DocXClassifier: High Performance Explainable Deep Network for Document Image Classification","date":"2022-03-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficient-document-image-classification-using","title":"Efficient Document Image Classification Using Region-Based Graph Neural Network","date":"2021-06-25","rows_on_this_dataset":7,"code_links":0,"syntology":null},{"paper":"/paper/light-weighted-cnn-for-text-classification","title":"Light-Weighted CNN for Text Classification","date":"2020-04-16","rows_on_this_dataset":3,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}