{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JCYKBTTLKXA7FWCYWY6HN7SE3K","short_pith_number":"pith:JCYKBTTL","schema_version":"1.0","canonical_sha256":"48b0a0ce6b55c1f2d858b63c76fe44daa8accd752d2efb04df0f2b22ade5739d","source":{"kind":"arxiv","id":"2203.10209","version":1},"attestation_state":"computed","paper":{"title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyu Liu, Dahua Lin, Kai Ding, Lianwen Jin, Mingxin Huang, Nicholas Yuan, Shenggao Zhu, Yuliang Liu, Zhenghao Peng","submitted_at":"2022-03-19T01:14:42Z","abstract_excerpt":"End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition. However, recent state-of-the-art methods usually incorporate detection and recognition simply by sharing the backbone, which does not directly take advantage of the feature interaction between the two tasks. In this paper, we propose a new end-to-end scene text spotting framework termed SwinTextSpotter. Using a transformer encoder with dynamic head as the detector, we unify the two tasks with a novel Recognition Convers"},"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":"2203.10209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-19T01:14:42Z","cross_cats_sorted":[],"title_canon_sha256":"e5553780a4461d5da92eddb6a9e4370049994686361d06d38edb7b499fbd8621","abstract_canon_sha256":"8ef9dd16e959da2ce0a986a2642e68662000ff8431893531e299a0199a4ab6cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:32.738734Z","signature_b64":"0TU70dCX1uwSE7vb2u6lYQbnMwYasBkrdd2ATjgSqPB9q9b+IW/mp1SS02on2NZliz3lB667q1DoZwdmhhpgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48b0a0ce6b55c1f2d858b63c76fe44daa8accd752d2efb04df0f2b22ade5739d","last_reissued_at":"2026-07-05T04:06:32.738272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:32.738272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyu Liu, Dahua Lin, Kai Ding, Lianwen Jin, Mingxin Huang, Nicholas Yuan, Shenggao Zhu, Yuliang Liu, Zhenghao Peng","submitted_at":"2022-03-19T01:14:42Z","abstract_excerpt":"End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition. However, recent state-of-the-art methods usually incorporate detection and recognition simply by sharing the backbone, which does not directly take advantage of the feature interaction between the two tasks. In this paper, we propose a new end-to-end scene text spotting framework termed SwinTextSpotter. Using a transformer encoder with dynamic head as the detector, we unify the two tasks with a novel Recognition Convers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10209","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.10209/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":"2203.10209","created_at":"2026-07-05T04:06:32.738340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10209v1","created_at":"2026-07-05T04:06:32.738340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10209","created_at":"2026-07-05T04:06:32.738340+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCYKBTTLKXA7","created_at":"2026-07-05T04:06:32.738340+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCYKBTTLKXA7FWCY","created_at":"2026-07-05T04:06:32.738340+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCYKBTTL","created_at":"2026-07-05T04:06:32.738340+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/JCYKBTTLKXA7FWCYWY6HN7SE3K","json":"https://pith.science/pith/JCYKBTTLKXA7FWCYWY6HN7SE3K.json","graph_json":"https://pith.science/api/pith-number/JCYKBTTLKXA7FWCYWY6HN7SE3K/graph.json","events_json":"https://pith.science/api/pith-number/JCYKBTTLKXA7FWCYWY6HN7SE3K/events.json","paper":"https://pith.science/paper/JCYKBTTL"},"agent_actions":{"view_html":"https://pith.science/pith/JCYKBTTLKXA7FWCYWY6HN7SE3K","download_json":"https://pith.science/pith/JCYKBTTLKXA7FWCYWY6HN7SE3K.json","view_paper":"https://pith.science/paper/JCYKBTTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10209&json=true","fetch_graph":"https://pith.science/api/pith-number/JCYKBTTLKXA7FWCYWY6HN7SE3K/graph.json","fetch_events":"https://pith.science/api/pith-number/JCYKBTTLKXA7FWCYWY6HN7SE3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCYKBTTLKXA7FWCYWY6HN7SE3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCYKBTTLKXA7FWCYWY6HN7SE3K/action/storage_attestation","attest_author":"https://pith.science/pith/JCYKBTTLKXA7FWCYWY6HN7SE3K/action/author_attestation","sign_citation":"https://pith.science/pith/JCYKBTTLKXA7FWCYWY6HN7SE3K/action/citation_signature","submit_replication":"https://pith.science/pith/JCYKBTTLKXA7FWCYWY6HN7SE3K/action/replication_record"}},"created_at":"2026-07-05T04:06:32.738340+00:00","updated_at":"2026-07-05T04:06:32.738340+00:00"}