{"url":"/dataset/dsse-200","name":"DSSE-200","full_name":null,"description_markdown":"The DSSE-200 is a complex document layout dataset including various dataset styles. The dataset contains 200 images from pictures, PPT, brochure documents, old newspapers and scanned documents.","description_withheld":null,"homepage":"http://personal.psu.edu/xuy111/projects/cvpr2017_doc.html","introduced_date":"2017-07-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-to-extract-semantic-structure-from-1","title":"Learning to Extract Semantic Structure From Documents Using Multimodal Fully Convolutional Neural Networks","first_author":"Xiao Yang","url":null},"license":null,"modalities":[],"tasks":[{"name":"Document Layout Analysis","url":"/task/document-layout-analysis","datasets_with_task":"/datasets/task/document-layout-analysis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DSSE-200"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}