{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IKQJSYDR5D2TX43JR37HKALQDK","short_pith_number":"pith:IKQJSYDR","schema_version":"1.0","canonical_sha256":"42a0996071e8f53bf3698efe7501701aa8f482aef3f4e3f4f563f8a1f02d988d","source":{"kind":"arxiv","id":"2107.12090","version":2},"attestation_state":"computed","paper":{"title":"Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amandeep Kumar, Aneeshan Sain, Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Shuvozit Ghose, Yi-Zhe Song","submitted_at":"2021-07-26T10:15:14Z","abstract_excerpt":"Although text recognition has significantly evolved over the years, state-of-the-art (SOTA) models still struggle in the wild scenarios due to complex backgrounds, varying fonts, uncontrolled illuminations, distortions and other artefacts. This is because such models solely depend on visual information for text recognition, thus lacking semantic reasoning capabilities. In this paper, we argue that semantic information offers a complementary role in addition to visual only. More specifically, we additionally utilize semantic information by proposing a multi-stage multi-scale attentional decoder"},"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":"2107.12090","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-26T10:15:14Z","cross_cats_sorted":[],"title_canon_sha256":"ea8b06c5bf480b232d54486473f5fb3f817adad02e6a73f9df56895e57697dfe","abstract_canon_sha256":"12ea8cf6c943a6effa4f60591331bba3fcfacbe3cf5032e432e6671d3c33cfbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:55.779669Z","signature_b64":"MbdYl32vvG9hNUAGwqMlsf5AZs/s/Vv+igOXtqiWydJZSlnMe/btyWoMcV9xJhGziaKrnecdtKByfh9HrltOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42a0996071e8f53bf3698efe7501701aa8f482aef3f4e3f4f563f8a1f02d988d","last_reissued_at":"2026-07-05T03:00:55.779193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:55.779193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amandeep Kumar, Aneeshan Sain, Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Shuvozit Ghose, Yi-Zhe Song","submitted_at":"2021-07-26T10:15:14Z","abstract_excerpt":"Although text recognition has significantly evolved over the years, state-of-the-art (SOTA) models still struggle in the wild scenarios due to complex backgrounds, varying fonts, uncontrolled illuminations, distortions and other artefacts. This is because such models solely depend on visual information for text recognition, thus lacking semantic reasoning capabilities. In this paper, we argue that semantic information offers a complementary role in addition to visual only. More specifically, we additionally utilize semantic information by proposing a multi-stage multi-scale attentional decoder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12090","kind":"arxiv","version":2},"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/2107.12090/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":"2107.12090","created_at":"2026-07-05T03:00:55.779248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12090v2","created_at":"2026-07-05T03:00:55.779248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12090","created_at":"2026-07-05T03:00:55.779248+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKQJSYDR5D2T","created_at":"2026-07-05T03:00:55.779248+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKQJSYDR5D2TX43J","created_at":"2026-07-05T03:00:55.779248+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKQJSYDR","created_at":"2026-07-05T03:00:55.779248+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/IKQJSYDR5D2TX43JR37HKALQDK","json":"https://pith.science/pith/IKQJSYDR5D2TX43JR37HKALQDK.json","graph_json":"https://pith.science/api/pith-number/IKQJSYDR5D2TX43JR37HKALQDK/graph.json","events_json":"https://pith.science/api/pith-number/IKQJSYDR5D2TX43JR37HKALQDK/events.json","paper":"https://pith.science/paper/IKQJSYDR"},"agent_actions":{"view_html":"https://pith.science/pith/IKQJSYDR5D2TX43JR37HKALQDK","download_json":"https://pith.science/pith/IKQJSYDR5D2TX43JR37HKALQDK.json","view_paper":"https://pith.science/paper/IKQJSYDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12090&json=true","fetch_graph":"https://pith.science/api/pith-number/IKQJSYDR5D2TX43JR37HKALQDK/graph.json","fetch_events":"https://pith.science/api/pith-number/IKQJSYDR5D2TX43JR37HKALQDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKQJSYDR5D2TX43JR37HKALQDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKQJSYDR5D2TX43JR37HKALQDK/action/storage_attestation","attest_author":"https://pith.science/pith/IKQJSYDR5D2TX43JR37HKALQDK/action/author_attestation","sign_citation":"https://pith.science/pith/IKQJSYDR5D2TX43JR37HKALQDK/action/citation_signature","submit_replication":"https://pith.science/pith/IKQJSYDR5D2TX43JR37HKALQDK/action/replication_record"}},"created_at":"2026-07-05T03:00:55.779248+00:00","updated_at":"2026-07-05T03:00:55.779248+00:00"}