{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LZSIQDFQOUG37RIHC5RIGV4MIM","short_pith_number":"pith:LZSIQDFQ","schema_version":"1.0","canonical_sha256":"5e64880cb0750dbfc507176283578c433ccbc8cc68ae0fc927d2e0050b09922a","source":{"kind":"arxiv","id":"2203.14215","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Mining with Scene Text for Fine-Grained Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Ren, Hao Liu, Hao Wang, Junchao Liao, Tianheng Cheng, Wenyu Liu, Xiang Bai, Zewen Gao","submitted_at":"2022-03-27T05:54:00Z","abstract_excerpt":"Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be irrelevant when it is not significantly related to objects/scenes. We propose an end-to-end trainable network that mines implicit contextual knowledge behind scene text image and enhance the semantics and correlation to fine-tune the image representation. Unlike the existing methods, our model integrates three modalities: visual feature extraction, text semantics ex"},"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":"2203.14215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-27T05:54:00Z","cross_cats_sorted":[],"title_canon_sha256":"63cae5377af082ea3a3efb4267f317fbf107db69c75e294f6d10eb0253c3db0e","abstract_canon_sha256":"dba31dbe0d5e74bc3084ad1d64a639bc89cbb96054482ba72cb24545b4e6f484"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:48.913812Z","signature_b64":"6PMVT/LXkiO/FPJVMZFjiZ16ZSb/cbMHj6hNeLTsgi3i4/nMCLoKBClfiNkoiH8VE9erdnndhCkPHJcXWnN9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e64880cb0750dbfc507176283578c433ccbc8cc68ae0fc927d2e0050b09922a","last_reissued_at":"2026-07-05T04:08:48.913393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:48.913393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Mining with Scene Text for Fine-Grained Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Ren, Hao Liu, Hao Wang, Junchao Liao, Tianheng Cheng, Wenyu Liu, Xiang Bai, Zewen Gao","submitted_at":"2022-03-27T05:54:00Z","abstract_excerpt":"Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be irrelevant when it is not significantly related to objects/scenes. We propose an end-to-end trainable network that mines implicit contextual knowledge behind scene text image and enhance the semantics and correlation to fine-tune the image representation. Unlike the existing methods, our model integrates three modalities: visual feature extraction, text semantics ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14215","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/2203.14215/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":"2203.14215","created_at":"2026-07-05T04:08:48.913452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14215v1","created_at":"2026-07-05T04:08:48.913452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14215","created_at":"2026-07-05T04:08:48.913452+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZSIQDFQOUG3","created_at":"2026-07-05T04:08:48.913452+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZSIQDFQOUG37RIH","created_at":"2026-07-05T04:08:48.913452+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZSIQDFQ","created_at":"2026-07-05T04:08:48.913452+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/LZSIQDFQOUG37RIHC5RIGV4MIM","json":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM.json","graph_json":"https://pith.science/api/pith-number/LZSIQDFQOUG37RIHC5RIGV4MIM/graph.json","events_json":"https://pith.science/api/pith-number/LZSIQDFQOUG37RIHC5RIGV4MIM/events.json","paper":"https://pith.science/paper/LZSIQDFQ"},"agent_actions":{"view_html":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM","download_json":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM.json","view_paper":"https://pith.science/paper/LZSIQDFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14215&json=true","fetch_graph":"https://pith.science/api/pith-number/LZSIQDFQOUG37RIHC5RIGV4MIM/graph.json","fetch_events":"https://pith.science/api/pith-number/LZSIQDFQOUG37RIHC5RIGV4MIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/action/storage_attestation","attest_author":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/action/author_attestation","sign_citation":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/action/citation_signature","submit_replication":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/action/replication_record"}},"created_at":"2026-07-05T04:08:48.913452+00:00","updated_at":"2026-07-05T04:08:48.913452+00:00"}