{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZRU4GZ5GVTW52DURC4NJMXXFNQ","short_pith_number":"pith:ZRU4GZ5G","schema_version":"1.0","canonical_sha256":"cc69c367a6aceddd0e91171a965ee56c05b217e2da216bfefb048505e4f49109","source":{"kind":"arxiv","id":"2402.17134","version":1},"attestation_state":"computed","paper":{"title":"Efficiently Leveraging Linguistic Priors for Scene Text Spotting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Nguyen Nguyen, Yapeng Tian","submitted_at":"2024-02-27T01:57:09Z","abstract_excerpt":"Incorporating linguistic knowledge can improve scene text recognition, but it is questionable whether the same holds for scene text spotting, which typically involves text detection and recognition. This paper proposes a method that leverages linguistic knowledge from a large text corpus to replace the traditional one-hot encoding used in auto-regressive scene text spotting and recognition models. This allows the model to capture the relationship between characters in the same word. Additionally, we introduce a technique to generate text distributions that align well with scene text datasets, "},"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":"2402.17134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-27T01:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"bad93133814a50571e9e181c49b7b885ea48d1c3ea5ff20cb54c13f464579487","abstract_canon_sha256":"97f59501712ff25df3968fd8657a58f3aab8caf75018acff187cdac626dcb923"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:43.018768Z","signature_b64":"ZNql6R1rroaEGQKqBiyP2tHlKGLj/HWyd70XYi5LHzJw9k0uzfRmqv6PYy6RmoC8fU00n+lWoW4tjgKAO0TJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc69c367a6aceddd0e91171a965ee56c05b217e2da216bfefb048505e4f49109","last_reissued_at":"2026-07-05T07:49:43.018224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:43.018224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficiently Leveraging Linguistic Priors for Scene Text Spotting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Nguyen Nguyen, Yapeng Tian","submitted_at":"2024-02-27T01:57:09Z","abstract_excerpt":"Incorporating linguistic knowledge can improve scene text recognition, but it is questionable whether the same holds for scene text spotting, which typically involves text detection and recognition. This paper proposes a method that leverages linguistic knowledge from a large text corpus to replace the traditional one-hot encoding used in auto-regressive scene text spotting and recognition models. This allows the model to capture the relationship between characters in the same word. Additionally, we introduce a technique to generate text distributions that align well with scene text datasets, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17134","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/2402.17134/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":"2402.17134","created_at":"2026-07-05T07:49:43.018279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17134v1","created_at":"2026-07-05T07:49:43.018279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17134","created_at":"2026-07-05T07:49:43.018279+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRU4GZ5GVTW5","created_at":"2026-07-05T07:49:43.018279+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRU4GZ5GVTW52DUR","created_at":"2026-07-05T07:49:43.018279+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRU4GZ5G","created_at":"2026-07-05T07:49:43.018279+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/ZRU4GZ5GVTW52DURC4NJMXXFNQ","json":"https://pith.science/pith/ZRU4GZ5GVTW52DURC4NJMXXFNQ.json","graph_json":"https://pith.science/api/pith-number/ZRU4GZ5GVTW52DURC4NJMXXFNQ/graph.json","events_json":"https://pith.science/api/pith-number/ZRU4GZ5GVTW52DURC4NJMXXFNQ/events.json","paper":"https://pith.science/paper/ZRU4GZ5G"},"agent_actions":{"view_html":"https://pith.science/pith/ZRU4GZ5GVTW52DURC4NJMXXFNQ","download_json":"https://pith.science/pith/ZRU4GZ5GVTW52DURC4NJMXXFNQ.json","view_paper":"https://pith.science/paper/ZRU4GZ5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17134&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRU4GZ5GVTW52DURC4NJMXXFNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRU4GZ5GVTW52DURC4NJMXXFNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRU4GZ5GVTW52DURC4NJMXXFNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRU4GZ5GVTW52DURC4NJMXXFNQ/action/storage_attestation","attest_author":"https://pith.science/pith/ZRU4GZ5GVTW52DURC4NJMXXFNQ/action/author_attestation","sign_citation":"https://pith.science/pith/ZRU4GZ5GVTW52DURC4NJMXXFNQ/action/citation_signature","submit_replication":"https://pith.science/pith/ZRU4GZ5GVTW52DURC4NJMXXFNQ/action/replication_record"}},"created_at":"2026-07-05T07:49:43.018279+00:00","updated_at":"2026-07-05T07:49:43.018279+00:00"}