{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UBPJLOJ6WBXLZNLZGRWYC4ZMCK","short_pith_number":"pith:UBPJLOJ6","schema_version":"1.0","canonical_sha256":"a05e95b93eb06ebcb579346d81732c12a5b09e7fe543c3cf38ec943ebe83985d","source":{"kind":"arxiv","id":"2308.10147","version":1},"attestation_state":"computed","paper":{"title":"ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Huang, Dezhi Peng, Hao Lu, Jiaxin Zhang, Lianwen Jin, Mingxin Huang, Xiang Bai, Yuliang Liu","submitted_at":"2023-08-20T03:22:23Z","abstract_excerpt":"In recent years, end-to-end scene text spotting approaches are evolving to the Transformer-based framework. While previous studies have shown the crucial importance of the intrinsic synergy between text detection and recognition, recent advances in Transformer-based methods usually adopt an implicit synergy strategy with shared query, which can not fully realize the potential of these two interactive tasks. In this paper, we argue that the explicit synergy considering distinct characteristics of text detection and recognition can significantly improve the performance text spotting. To this end"},"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":"2308.10147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T03:22:23Z","cross_cats_sorted":[],"title_canon_sha256":"1293fcad50c541ab171494ba2d57610585ed73461f2ec31e7c94aae8c1fd45ad","abstract_canon_sha256":"758965b981a191163bb07a70ab29618037ca87469a1113b763cc356e825a9ccf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:52.164433Z","signature_b64":"hwAJEJWuWOQMOeOsg2ixpe4U/NhwgoqP7kNgkTubBpRA+yZf+jF7lstbqirpfx6TEDTDtMkPJHbj8hA4Z/ZCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a05e95b93eb06ebcb579346d81732c12a5b09e7fe543c3cf38ec943ebe83985d","last_reissued_at":"2026-07-05T06:42:52.164011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:52.164011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Huang, Dezhi Peng, Hao Lu, Jiaxin Zhang, Lianwen Jin, Mingxin Huang, Xiang Bai, Yuliang Liu","submitted_at":"2023-08-20T03:22:23Z","abstract_excerpt":"In recent years, end-to-end scene text spotting approaches are evolving to the Transformer-based framework. While previous studies have shown the crucial importance of the intrinsic synergy between text detection and recognition, recent advances in Transformer-based methods usually adopt an implicit synergy strategy with shared query, which can not fully realize the potential of these two interactive tasks. In this paper, we argue that the explicit synergy considering distinct characteristics of text detection and recognition can significantly improve the performance text spotting. To this end"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10147","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/2308.10147/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":"2308.10147","created_at":"2026-07-05T06:42:52.164071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10147v1","created_at":"2026-07-05T06:42:52.164071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10147","created_at":"2026-07-05T06:42:52.164071+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBPJLOJ6WBXL","created_at":"2026-07-05T06:42:52.164071+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBPJLOJ6WBXLZNLZ","created_at":"2026-07-05T06:42:52.164071+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBPJLOJ6","created_at":"2026-07-05T06:42:52.164071+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/UBPJLOJ6WBXLZNLZGRWYC4ZMCK","json":"https://pith.science/pith/UBPJLOJ6WBXLZNLZGRWYC4ZMCK.json","graph_json":"https://pith.science/api/pith-number/UBPJLOJ6WBXLZNLZGRWYC4ZMCK/graph.json","events_json":"https://pith.science/api/pith-number/UBPJLOJ6WBXLZNLZGRWYC4ZMCK/events.json","paper":"https://pith.science/paper/UBPJLOJ6"},"agent_actions":{"view_html":"https://pith.science/pith/UBPJLOJ6WBXLZNLZGRWYC4ZMCK","download_json":"https://pith.science/pith/UBPJLOJ6WBXLZNLZGRWYC4ZMCK.json","view_paper":"https://pith.science/paper/UBPJLOJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10147&json=true","fetch_graph":"https://pith.science/api/pith-number/UBPJLOJ6WBXLZNLZGRWYC4ZMCK/graph.json","fetch_events":"https://pith.science/api/pith-number/UBPJLOJ6WBXLZNLZGRWYC4ZMCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBPJLOJ6WBXLZNLZGRWYC4ZMCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBPJLOJ6WBXLZNLZGRWYC4ZMCK/action/storage_attestation","attest_author":"https://pith.science/pith/UBPJLOJ6WBXLZNLZGRWYC4ZMCK/action/author_attestation","sign_citation":"https://pith.science/pith/UBPJLOJ6WBXLZNLZGRWYC4ZMCK/action/citation_signature","submit_replication":"https://pith.science/pith/UBPJLOJ6WBXLZNLZGRWYC4ZMCK/action/replication_record"}},"created_at":"2026-07-05T06:42:52.164071+00:00","updated_at":"2026-07-05T06:42:52.164071+00:00"}