{"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/multimodal-deep-networks-for-text-and-image","title":"Multimodal deep networks for text and image-based document classification","arxiv_id":"1907.06370","date":"2019-07-15","proceeding":null,"authors":["Nicolas Audebert","Catherine Herold","Kuider Slimani","Cédric Vidal"],"abstract":"Classification of document images is a critical step for archival of old manuscripts, online subscription and administrative procedures. Computer vision and deep learning have been suggested as a first solution to classify documents based on their visual appearance. However, achieving the fine-grained classification that is required in real-world setting cannot be achieved by visual analysis alone. Often, the relevant information is in the actual text content of the document. We design a multimodal neural network that is able to learn from word embeddings, computed on text extracted by OCR, and from the image. We show that this approach boosts pure image accuracy by 3% on Tobacco3482 and RVL-CDIP augmented by our new QS-OCR text dataset (https://github.com/Quicksign/ocrized-text-dataset), even without clean text information.","url_abs":"https://arxiv.org/abs/1907.06370v1","url_pdf":"https://arxiv.org/pdf/1907.06370v1.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":"multimodal-deep-networks-for-text-and-image","repo_url":"https://github.com/Quicksign/ocrized-text-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multimodal-deep-networks-for-text-and-image","repo_url":"https://github.com/mleimeister/document-image-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multimodal-deep-networks-for-text-and-image","repo_url":"https://github.com/bharathrajcl/Multimodal-deep-networks-for-text-and-image-based-document-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multimodal-deep-learning","task_name":"Multimodal Deep Learning"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.06370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.06370"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mleimeister/document-image-classification","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bharathrajcl/Multimodal-deep-networks-for-text-and-image-based-document-classification","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Quicksign/ocrized-text-dataset","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"73d171a02315a040","entry":"remove_punct","repo":"bharathrajcl/Multimodal-deep-networks-for-text-and-image-based-document-classification","repo_kind":"listed","path":"dataset_creation.py","file_url":"https://github.com/bharathrajcl/Multimodal-deep-networks-for-text-and-image-based-document-classification/blob/HEAD/dataset_creation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"73d171a02315a040"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}