{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LV7NZUXGIONLETEXALRA6ZMCTQ","short_pith_number":"pith:LV7NZUXG","schema_version":"1.0","canonical_sha256":"5d7edcd2e6439ab24c9702e20f65829c32b85ee34fe1aa0b4bf8ef2759fbd722","source":{"kind":"arxiv","id":"1812.01393","version":2},"attestation_state":"computed","paper":{"title":"TextField: Learning A Deep Direction Field for Irregular Scene Text Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wei Zhou, Xiang Bai, Yongchao Xu, Yongpan Wang, Yukang Wang, Zhibo Yang","submitted_at":"2018-12-04T13:12:58Z","abstract_excerpt":"Scene text detection is an important step of scene text reading system. The main challenges lie on significantly varied sizes and aspect ratios, arbitrary orientations and shapes. Driven by recent progress in deep learning, impressive performances have been achieved for multi-oriented text detection. Yet, the performance drops dramatically in detecting curved texts due to the limited text representation (e.g., horizontal bounding boxes, rotated rectangles, or quadrilaterals). It is of great interest to detect curved texts, which are actually very common in natural scenes. In this paper, we pre"},"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":"1812.01393","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-04T13:12:58Z","cross_cats_sorted":[],"title_canon_sha256":"bb4514f4d3826dde556d2e2be54dbd98a2f76dbf93b371e78a00a998b7861952","abstract_canon_sha256":"801cb6191386621421dab3ea835e840deb9d67114f915ecb813fd15b9fc51755"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:08:25.443955Z","signature_b64":"1f1sgDvTC52TukuN7bq8+ncdYeSzPbYRJoIKxchyT8Pm9AzLB71QRfY4nbxWBTH+3QENAxZtvioAy3T5Nhh0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d7edcd2e6439ab24c9702e20f65829c32b85ee34fe1aa0b4bf8ef2759fbd722","last_reissued_at":"2026-07-05T00:08:25.443565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:08:25.443565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextField: Learning A Deep Direction Field for Irregular Scene Text Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wei Zhou, Xiang Bai, Yongchao Xu, Yongpan Wang, Yukang Wang, Zhibo Yang","submitted_at":"2018-12-04T13:12:58Z","abstract_excerpt":"Scene text detection is an important step of scene text reading system. The main challenges lie on significantly varied sizes and aspect ratios, arbitrary orientations and shapes. Driven by recent progress in deep learning, impressive performances have been achieved for multi-oriented text detection. Yet, the performance drops dramatically in detecting curved texts due to the limited text representation (e.g., horizontal bounding boxes, rotated rectangles, or quadrilaterals). It is of great interest to detect curved texts, which are actually very common in natural scenes. In this paper, we pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01393","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1812.01393/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1812.01393","created_at":"2026-07-05T00:08:25.443623+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01393v2","created_at":"2026-07-05T00:08:25.443623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01393","created_at":"2026-07-05T00:08:25.443623+00:00"},{"alias_kind":"pith_short_12","alias_value":"LV7NZUXGIONL","created_at":"2026-07-05T00:08:25.443623+00:00"},{"alias_kind":"pith_short_16","alias_value":"LV7NZUXGIONLETEX","created_at":"2026-07-05T00:08:25.443623+00:00"},{"alias_kind":"pith_short_8","alias_value":"LV7NZUXG","created_at":"2026-07-05T00:08:25.443623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.05498","citing_title":"A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LV7NZUXGIONLETEXALRA6ZMCTQ","json":"https://pith.science/pith/LV7NZUXGIONLETEXALRA6ZMCTQ.json","graph_json":"https://pith.science/api/pith-number/LV7NZUXGIONLETEXALRA6ZMCTQ/graph.json","events_json":"https://pith.science/api/pith-number/LV7NZUXGIONLETEXALRA6ZMCTQ/events.json","paper":"https://pith.science/paper/LV7NZUXG"},"agent_actions":{"view_html":"https://pith.science/pith/LV7NZUXGIONLETEXALRA6ZMCTQ","download_json":"https://pith.science/pith/LV7NZUXGIONLETEXALRA6ZMCTQ.json","view_paper":"https://pith.science/paper/LV7NZUXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01393&json=true","fetch_graph":"https://pith.science/api/pith-number/LV7NZUXGIONLETEXALRA6ZMCTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LV7NZUXGIONLETEXALRA6ZMCTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LV7NZUXGIONLETEXALRA6ZMCTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LV7NZUXGIONLETEXALRA6ZMCTQ/action/storage_attestation","attest_author":"https://pith.science/pith/LV7NZUXGIONLETEXALRA6ZMCTQ/action/author_attestation","sign_citation":"https://pith.science/pith/LV7NZUXGIONLETEXALRA6ZMCTQ/action/citation_signature","submit_replication":"https://pith.science/pith/LV7NZUXGIONLETEXALRA6ZMCTQ/action/replication_record"}},"created_at":"2026-07-05T00:08:25.443623+00:00","updated_at":"2026-07-05T00:08:25.443623+00:00"}