{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3M6HBF26I7I2TXF2STCFGKH6IJ","short_pith_number":"pith:3M6HBF26","schema_version":"1.0","canonical_sha256":"db3c70975e47d1a9dcba94c45328fe425c8b466321f305b758c101eac1514b03","source":{"kind":"arxiv","id":"1706.09579","version":2},"attestation_state":"computed","paper":{"title":"R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hua Wang, Pei Fu, Shuli Yang, Wei Li, Xiangyu Zhu, Xiaobing Wang, Yingying Jiang, Zhenbo Luo","submitted_at":"2017-06-29T05:00:38Z","abstract_excerpt":"In this paper, we propose a novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images. The framework is based on Faster R-CNN [1] architecture. First, we use the Region Proposal Network (RPN) to generate axis-aligned bounding boxes that enclose the texts with different orientations. Second, for each axis-aligned text box proposed by RPN, we extract its pooled features with different pooled sizes and the concatenated features are used to simultaneously predict the text/non-text score, axis-aligned box and inclined minimum area box. At last,"},"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":"1706.09579","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-29T05:00:38Z","cross_cats_sorted":[],"title_canon_sha256":"46e3c083d9e24d80af973b1918ae9270264e6fed87cbced7209aaf1d18618e71","abstract_canon_sha256":"4752731689138b796aeb6c58ba756a590ee5725ba28851134dd98920b624b775"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:12.047449Z","signature_b64":"DgZK+jtEKf8wZIpV5A/1vmr/XY3rOE4/OtiBzcDXPh6UbtQn4WEhiq0zGrJF4NUPy/7hPzar5I6yT1raFIxpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db3c70975e47d1a9dcba94c45328fe425c8b466321f305b758c101eac1514b03","last_reissued_at":"2026-05-18T00:41:12.046841Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:12.046841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hua Wang, Pei Fu, Shuli Yang, Wei Li, Xiangyu Zhu, Xiaobing Wang, Yingying Jiang, Zhenbo Luo","submitted_at":"2017-06-29T05:00:38Z","abstract_excerpt":"In this paper, we propose a novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images. The framework is based on Faster R-CNN [1] architecture. First, we use the Region Proposal Network (RPN) to generate axis-aligned bounding boxes that enclose the texts with different orientations. Second, for each axis-aligned text box proposed by RPN, we extract its pooled features with different pooled sizes and the concatenated features are used to simultaneously predict the text/non-text score, axis-aligned box and inclined minimum area box. At last,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.09579","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":""},"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":"1706.09579","created_at":"2026-05-18T00:41:12.046929+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.09579v2","created_at":"2026-05-18T00:41:12.046929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.09579","created_at":"2026-05-18T00:41:12.046929+00:00"},{"alias_kind":"pith_short_12","alias_value":"3M6HBF26I7I2","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3M6HBF26I7I2TXF2","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3M6HBF26","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3M6HBF26I7I2TXF2STCFGKH6IJ","json":"https://pith.science/pith/3M6HBF26I7I2TXF2STCFGKH6IJ.json","graph_json":"https://pith.science/api/pith-number/3M6HBF26I7I2TXF2STCFGKH6IJ/graph.json","events_json":"https://pith.science/api/pith-number/3M6HBF26I7I2TXF2STCFGKH6IJ/events.json","paper":"https://pith.science/paper/3M6HBF26"},"agent_actions":{"view_html":"https://pith.science/pith/3M6HBF26I7I2TXF2STCFGKH6IJ","download_json":"https://pith.science/pith/3M6HBF26I7I2TXF2STCFGKH6IJ.json","view_paper":"https://pith.science/paper/3M6HBF26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.09579&json=true","fetch_graph":"https://pith.science/api/pith-number/3M6HBF26I7I2TXF2STCFGKH6IJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3M6HBF26I7I2TXF2STCFGKH6IJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3M6HBF26I7I2TXF2STCFGKH6IJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3M6HBF26I7I2TXF2STCFGKH6IJ/action/storage_attestation","attest_author":"https://pith.science/pith/3M6HBF26I7I2TXF2STCFGKH6IJ/action/author_attestation","sign_citation":"https://pith.science/pith/3M6HBF26I7I2TXF2STCFGKH6IJ/action/citation_signature","submit_replication":"https://pith.science/pith/3M6HBF26I7I2TXF2STCFGKH6IJ/action/replication_record"}},"created_at":"2026-05-18T00:41:12.046929+00:00","updated_at":"2026-05-18T00:41:12.046929+00:00"}