{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TODQWFYRBHIIWTRG2TN3X4SZHO","short_pith_number":"pith:TODQWFYR","schema_version":"1.0","canonical_sha256":"9b870b171109d08b4e26d4dbbbf2593baa61ca99d4e2681662e61024bc9d4397","source":{"kind":"arxiv","id":"1903.10412","version":1},"attestation_state":"computed","paper":{"title":"ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongsheng Zhang, Feifei Fu, George Almpanidis, Guowen Peng, Ke Chen, Wei Jiang, Yuefeng Tao","submitted_at":"2019-03-25T15:52:32Z","abstract_excerpt":"In this paper, we introduce the ShopSign dataset, which is a newly developed natural scene text dataset of Chinese shop signs in street views. Although a few scene text datasets are already publicly available (e.g. ICDAR2015, COCO-Text), there are few images in these datasets that contain Chinese texts/characters. Hence, we collect and annotate the ShopSign dataset to advance research in Chinese scene text detection and recognition.\n  The new dataset has three distinctive characteristics: (1) large-scale: it contains 25,362 Chinese shop sign images, with a total number of 196,010 text-lines. ("},"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":"1903.10412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-25T15:52:32Z","cross_cats_sorted":[],"title_canon_sha256":"eb7ac9d31a8a9c1fe35d8e505b7fc35ef3a82245235246564571b2373a7e17c6","abstract_canon_sha256":"b74a7331c2f3d85e8db3f7b0bfb8b52dde364bb069bb9c4f4bbe7f59277468d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:29.491927Z","signature_b64":"b7pOlTip2L5Mv3+r2f4RjgrZrGgGOBu1XKIKlyzk9Ee+N23F2xaNFDaoAovkeMmUiV5wMQfxvt9dL2TRJ4R+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b870b171109d08b4e26d4dbbbf2593baa61ca99d4e2681662e61024bc9d4397","last_reissued_at":"2026-05-17T23:50:29.491092Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:29.491092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongsheng Zhang, Feifei Fu, George Almpanidis, Guowen Peng, Ke Chen, Wei Jiang, Yuefeng Tao","submitted_at":"2019-03-25T15:52:32Z","abstract_excerpt":"In this paper, we introduce the ShopSign dataset, which is a newly developed natural scene text dataset of Chinese shop signs in street views. Although a few scene text datasets are already publicly available (e.g. ICDAR2015, COCO-Text), there are few images in these datasets that contain Chinese texts/characters. Hence, we collect and annotate the ShopSign dataset to advance research in Chinese scene text detection and recognition.\n  The new dataset has three distinctive characteristics: (1) large-scale: it contains 25,362 Chinese shop sign images, with a total number of 196,010 text-lines. ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10412","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":"1903.10412","created_at":"2026-05-17T23:50:29.491238+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.10412v1","created_at":"2026-05-17T23:50:29.491238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10412","created_at":"2026-05-17T23:50:29.491238+00:00"},{"alias_kind":"pith_short_12","alias_value":"TODQWFYRBHII","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TODQWFYRBHIIWTRG","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TODQWFYR","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2409.01704","citing_title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TODQWFYRBHIIWTRG2TN3X4SZHO","json":"https://pith.science/pith/TODQWFYRBHIIWTRG2TN3X4SZHO.json","graph_json":"https://pith.science/api/pith-number/TODQWFYRBHIIWTRG2TN3X4SZHO/graph.json","events_json":"https://pith.science/api/pith-number/TODQWFYRBHIIWTRG2TN3X4SZHO/events.json","paper":"https://pith.science/paper/TODQWFYR"},"agent_actions":{"view_html":"https://pith.science/pith/TODQWFYRBHIIWTRG2TN3X4SZHO","download_json":"https://pith.science/pith/TODQWFYRBHIIWTRG2TN3X4SZHO.json","view_paper":"https://pith.science/paper/TODQWFYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.10412&json=true","fetch_graph":"https://pith.science/api/pith-number/TODQWFYRBHIIWTRG2TN3X4SZHO/graph.json","fetch_events":"https://pith.science/api/pith-number/TODQWFYRBHIIWTRG2TN3X4SZHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TODQWFYRBHIIWTRG2TN3X4SZHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TODQWFYRBHIIWTRG2TN3X4SZHO/action/storage_attestation","attest_author":"https://pith.science/pith/TODQWFYRBHIIWTRG2TN3X4SZHO/action/author_attestation","sign_citation":"https://pith.science/pith/TODQWFYRBHIIWTRG2TN3X4SZHO/action/citation_signature","submit_replication":"https://pith.science/pith/TODQWFYRBHIIWTRG2TN3X4SZHO/action/replication_record"}},"created_at":"2026-05-17T23:50:29.491238+00:00","updated_at":"2026-05-17T23:50:29.491238+00:00"}