{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XBS6RLO2AOM6GODV2G2HZFLYN2","short_pith_number":"pith:XBS6RLO2","schema_version":"1.0","canonical_sha256":"b865e8adda0399e33875d1b47c95786e814f5dd2597f793fee86cfac4237c2d3","source":{"kind":"arxiv","id":"1604.06646","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Data for Text Localisation in Natural Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Ankush Gupta","submitted_at":"2016-04-22T13:23:08Z","abstract_excerpt":"In this paper we introduce a new method for text detection in natural images. The method comprises two contributions: First, a fast and scalable engine to generate synthetic images of text in clutter. This engine overlays synthetic text to existing background images in a natural way, accounting for the local 3D scene geometry. Second, we use the synthetic images to train a Fully-Convolutional Regression Network (FCRN) which efficiently performs text detection and bounding-box regression at all locations and multiple scales in an image. We discuss the relation of FCRN to the recently-introduced"},"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":"1604.06646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-22T13:23:08Z","cross_cats_sorted":[],"title_canon_sha256":"647023386aca46f21a49072ac641c2f10663964340993cf5080c1b70991284fd","abstract_canon_sha256":"18f3fb1013a3b91dffe358b25f949afe3c20de5031a6504b7a7fe3e03a5ae1c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:28.536600Z","signature_b64":"JWQvlwVJ8+lkL9hdWg9/5XqgFB5ftZZkhv3WsUBvS/Z3Wij29Qz5/Zt6FaRBS1yALFYg1YwbmD8iIyBm4np3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b865e8adda0399e33875d1b47c95786e814f5dd2597f793fee86cfac4237c2d3","last_reissued_at":"2026-05-18T01:16:28.536088Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:28.536088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Data for Text Localisation in Natural Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Ankush Gupta","submitted_at":"2016-04-22T13:23:08Z","abstract_excerpt":"In this paper we introduce a new method for text detection in natural images. The method comprises two contributions: First, a fast and scalable engine to generate synthetic images of text in clutter. This engine overlays synthetic text to existing background images in a natural way, accounting for the local 3D scene geometry. Second, we use the synthetic images to train a Fully-Convolutional Regression Network (FCRN) which efficiently performs text detection and bounding-box regression at all locations and multiple scales in an image. We discuss the relation of FCRN to the recently-introduced"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.06646","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":"1604.06646","created_at":"2026-05-18T01:16:28.536193+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.06646v1","created_at":"2026-05-18T01:16:28.536193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.06646","created_at":"2026-05-18T01:16:28.536193+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBS6RLO2AOM6","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBS6RLO2AOM6GODV","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBS6RLO2","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.01372","citing_title":"Improving Performance of End-to-End ASR on Numeric Sequences","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18173","citing_title":"Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBS6RLO2AOM6GODV2G2HZFLYN2","json":"https://pith.science/pith/XBS6RLO2AOM6GODV2G2HZFLYN2.json","graph_json":"https://pith.science/api/pith-number/XBS6RLO2AOM6GODV2G2HZFLYN2/graph.json","events_json":"https://pith.science/api/pith-number/XBS6RLO2AOM6GODV2G2HZFLYN2/events.json","paper":"https://pith.science/paper/XBS6RLO2"},"agent_actions":{"view_html":"https://pith.science/pith/XBS6RLO2AOM6GODV2G2HZFLYN2","download_json":"https://pith.science/pith/XBS6RLO2AOM6GODV2G2HZFLYN2.json","view_paper":"https://pith.science/paper/XBS6RLO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.06646&json=true","fetch_graph":"https://pith.science/api/pith-number/XBS6RLO2AOM6GODV2G2HZFLYN2/graph.json","fetch_events":"https://pith.science/api/pith-number/XBS6RLO2AOM6GODV2G2HZFLYN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBS6RLO2AOM6GODV2G2HZFLYN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBS6RLO2AOM6GODV2G2HZFLYN2/action/storage_attestation","attest_author":"https://pith.science/pith/XBS6RLO2AOM6GODV2G2HZFLYN2/action/author_attestation","sign_citation":"https://pith.science/pith/XBS6RLO2AOM6GODV2G2HZFLYN2/action/citation_signature","submit_replication":"https://pith.science/pith/XBS6RLO2AOM6GODV2G2HZFLYN2/action/replication_record"}},"created_at":"2026-05-18T01:16:28.536193+00:00","updated_at":"2026-05-18T01:16:28.536193+00:00"}