{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NKDCE5ZABE4TL5EFQQZSJCTPXB","short_pith_number":"pith:NKDCE5ZA","schema_version":"1.0","canonical_sha256":"6a86227720093935f4858433248a6fb86fc90af023bf1fd38c0c55b5ead31291","source":{"kind":"arxiv","id":"2108.09661","version":1},"attestation_state":"computed","paper":{"title":"From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongtao Xie, Jing Wang, Shancheng Fang, Shenggao Zhu, Yongdong Zhang, Yuxin Wang","submitted_at":"2021-08-22T07:56:24Z","abstract_excerpt":"In this paper, we abandon the dominant complex language model and rethink the linguistic learning process in the scene text recognition. Different from previous methods considering the visual and linguistic information in two separate structures, we propose a Visual Language Modeling Network (VisionLAN), which views the visual and linguistic information as a union by directly enduing the vision model with language capability. Specially, we introduce the text recognition of character-wise occluded feature maps in the training stage. Such operation guides the vision model to use not only the vis"},"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":"2108.09661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-22T07:56:24Z","cross_cats_sorted":[],"title_canon_sha256":"f30efd16c197f4752d399d90c6cdc0c4bd3fe91cf86c628c4c0b985587180431","abstract_canon_sha256":"11b3e8d11956a1a8d0f37f00b4da6fb6d1b51f3215b7857a299beb65b958c6cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:56.887361Z","signature_b64":"i8wEEJ7NgT7+EK6ginFJ0ycIH6a4B8IQ8RCxapRFots0GlZm3eMPmrGk/Cp15v7cOOeO37TVi7AoDFelDAftBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a86227720093935f4858433248a6fb86fc90af023bf1fd38c0c55b5ead31291","last_reissued_at":"2026-07-05T03:07:56.886969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:56.886969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongtao Xie, Jing Wang, Shancheng Fang, Shenggao Zhu, Yongdong Zhang, Yuxin Wang","submitted_at":"2021-08-22T07:56:24Z","abstract_excerpt":"In this paper, we abandon the dominant complex language model and rethink the linguistic learning process in the scene text recognition. Different from previous methods considering the visual and linguistic information in two separate structures, we propose a Visual Language Modeling Network (VisionLAN), which views the visual and linguistic information as a union by directly enduing the vision model with language capability. Specially, we introduce the text recognition of character-wise occluded feature maps in the training stage. Such operation guides the vision model to use not only the vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09661","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/2108.09661/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":"2108.09661","created_at":"2026-07-05T03:07:56.887031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.09661v1","created_at":"2026-07-05T03:07:56.887031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09661","created_at":"2026-07-05T03:07:56.887031+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKDCE5ZABE4T","created_at":"2026-07-05T03:07:56.887031+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKDCE5ZABE4TL5EF","created_at":"2026-07-05T03:07:56.887031+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKDCE5ZA","created_at":"2026-07-05T03:07:56.887031+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/NKDCE5ZABE4TL5EFQQZSJCTPXB","json":"https://pith.science/pith/NKDCE5ZABE4TL5EFQQZSJCTPXB.json","graph_json":"https://pith.science/api/pith-number/NKDCE5ZABE4TL5EFQQZSJCTPXB/graph.json","events_json":"https://pith.science/api/pith-number/NKDCE5ZABE4TL5EFQQZSJCTPXB/events.json","paper":"https://pith.science/paper/NKDCE5ZA"},"agent_actions":{"view_html":"https://pith.science/pith/NKDCE5ZABE4TL5EFQQZSJCTPXB","download_json":"https://pith.science/pith/NKDCE5ZABE4TL5EFQQZSJCTPXB.json","view_paper":"https://pith.science/paper/NKDCE5ZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.09661&json=true","fetch_graph":"https://pith.science/api/pith-number/NKDCE5ZABE4TL5EFQQZSJCTPXB/graph.json","fetch_events":"https://pith.science/api/pith-number/NKDCE5ZABE4TL5EFQQZSJCTPXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKDCE5ZABE4TL5EFQQZSJCTPXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKDCE5ZABE4TL5EFQQZSJCTPXB/action/storage_attestation","attest_author":"https://pith.science/pith/NKDCE5ZABE4TL5EFQQZSJCTPXB/action/author_attestation","sign_citation":"https://pith.science/pith/NKDCE5ZABE4TL5EFQQZSJCTPXB/action/citation_signature","submit_replication":"https://pith.science/pith/NKDCE5ZABE4TL5EFQQZSJCTPXB/action/replication_record"}},"created_at":"2026-07-05T03:07:56.887031+00:00","updated_at":"2026-07-05T03:07:56.887031+00:00"}