{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XVAYCRT5Y4DUISCM4DVQR57JFC","short_pith_number":"pith:XVAYCRT5","schema_version":"1.0","canonical_sha256":"bd4181467dc70744484ce0eb08f7e928ba565b7bd30bbde7c3d409ab61a816a9","source":{"kind":"arxiv","id":"1611.06779","version":1},"attestation_state":"computed","paper":{"title":"TextBoxes: A Fast Text Detector with a Single Deep Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoguang Shi, Minghui Liao, Wenyu Liu, Xiang Bai, Xinggang Wang","submitted_at":"2016-11-21T13:35:15Z","abstract_excerpt":"This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression. TextBoxes outperforms competing methods in terms of text localization accuracy and is much faster, taking only 0.09s per image in a fast implementation. Furthermore, combined with a text recognizer, TextBoxes significantly outperforms state-of-the-art approaches on word spotting and end-to-end text recognition tasks."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1611.06779","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-21T13:35:15Z","cross_cats_sorted":[],"title_canon_sha256":"0ea319e226f7b89542c0a39607e439823fa6e56a13593ffdd8e9c46622a4df2c","abstract_canon_sha256":"2476e0bc752b81744d15019950d0927f8b55c9edb4d3f65b9f439bda8543d242"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:32.909391Z","signature_b64":"snrsGfJb+/uVcg34c0VbtOimj6OmxmdrgtfjFDgXmdCayQA38vQofnLwf8kETCCDeErff2Hh5xr+kORr/YlHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd4181467dc70744484ce0eb08f7e928ba565b7bd30bbde7c3d409ab61a816a9","last_reissued_at":"2026-05-18T00:57:32.908892Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:32.908892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextBoxes: A Fast Text Detector with a Single Deep Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoguang Shi, Minghui Liao, Wenyu Liu, Xiang Bai, Xinggang Wang","submitted_at":"2016-11-21T13:35:15Z","abstract_excerpt":"This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression. TextBoxes outperforms competing methods in terms of text localization accuracy and is much faster, taking only 0.09s per image in a fast implementation. Furthermore, combined with a text recognizer, TextBoxes significantly outperforms state-of-the-art approaches on word spotting and end-to-end text recognition tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06779","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1611.06779","created_at":"2026-05-18T00:57:32.908965+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.06779v1","created_at":"2026-05-18T00:57:32.908965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06779","created_at":"2026-05-18T00:57:32.908965+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVAYCRT5Y4DU","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVAYCRT5Y4DUISCM","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVAYCRT5","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09266","citing_title":"A Multitask Network for Localization and Recognition of Text in Images","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVAYCRT5Y4DUISCM4DVQR57JFC","json":"https://pith.science/pith/XVAYCRT5Y4DUISCM4DVQR57JFC.json","graph_json":"https://pith.science/api/pith-number/XVAYCRT5Y4DUISCM4DVQR57JFC/graph.json","events_json":"https://pith.science/api/pith-number/XVAYCRT5Y4DUISCM4DVQR57JFC/events.json","paper":"https://pith.science/paper/XVAYCRT5"},"agent_actions":{"view_html":"https://pith.science/pith/XVAYCRT5Y4DUISCM4DVQR57JFC","download_json":"https://pith.science/pith/XVAYCRT5Y4DUISCM4DVQR57JFC.json","view_paper":"https://pith.science/paper/XVAYCRT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.06779&json=true","fetch_graph":"https://pith.science/api/pith-number/XVAYCRT5Y4DUISCM4DVQR57JFC/graph.json","fetch_events":"https://pith.science/api/pith-number/XVAYCRT5Y4DUISCM4DVQR57JFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVAYCRT5Y4DUISCM4DVQR57JFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVAYCRT5Y4DUISCM4DVQR57JFC/action/storage_attestation","attest_author":"https://pith.science/pith/XVAYCRT5Y4DUISCM4DVQR57JFC/action/author_attestation","sign_citation":"https://pith.science/pith/XVAYCRT5Y4DUISCM4DVQR57JFC/action/citation_signature","submit_replication":"https://pith.science/pith/XVAYCRT5Y4DUISCM4DVQR57JFC/action/replication_record"}},"created_at":"2026-05-18T00:57:32.908965+00:00","updated_at":"2026-05-18T00:57:32.908965+00:00"}