{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HTKIPACDRORQAYY7UJNMLQS2EM","short_pith_number":"pith:HTKIPACD","schema_version":"1.0","canonical_sha256":"3cd48780438ba300631fa25ac5c25a233e4b78e7e599626a6418b6c349a74e72","source":{"kind":"arxiv","id":"2308.10408","version":1},"attestation_state":"computed","paper":{"title":"Turning a CLIP Model into a Scene Text Spotter","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Cao, Wenwen Yu, Xiang Bai, Xingkui Zhu, Xing Sun, Yuliang Liu","submitted_at":"2023-08-21T01:25:48Z","abstract_excerpt":"We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone utilizes visual prompt learning and cross-attention in CLIP to extract image and text-based prior knowledge. Using predefined and learnable prompts, FastTCM-CR50 introduces an instance-language matching process to enhance the synergy between image and text embeddings, thereby refining text regions. Our Bimodal Similarity Matching (BSM) module facilitates dynamic language prompt gen"},"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":"2308.10408","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T01:25:48Z","cross_cats_sorted":[],"title_canon_sha256":"178415172cbc5bce4918b3a105c091aacf908ec0d8c2e3dc76a31ef256eef2bb","abstract_canon_sha256":"f1a8b5dfa0b7d9aa4cbf35ee86aeec21977b183943bfb83b2774f590e20e2f67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:08.771239Z","signature_b64":"Ua++267Mg28u8IGY61VecogRvtaD3SMl1Jf1Ce5BmhTv4huq9H7UDFQsYO6+MFVOIr/Bc9jX1IIRHb70MB8sAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cd48780438ba300631fa25ac5c25a233e4b78e7e599626a6418b6c349a74e72","last_reissued_at":"2026-07-05T06:43:08.770893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:08.770893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Turning a CLIP Model into a Scene Text Spotter","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Cao, Wenwen Yu, Xiang Bai, Xingkui Zhu, Xing Sun, Yuliang Liu","submitted_at":"2023-08-21T01:25:48Z","abstract_excerpt":"We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone utilizes visual prompt learning and cross-attention in CLIP to extract image and text-based prior knowledge. Using predefined and learnable prompts, FastTCM-CR50 introduces an instance-language matching process to enhance the synergy between image and text embeddings, thereby refining text regions. Our Bimodal Similarity Matching (BSM) module facilitates dynamic language prompt gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10408","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/2308.10408/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":"2308.10408","created_at":"2026-07-05T06:43:08.770940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10408v1","created_at":"2026-07-05T06:43:08.770940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10408","created_at":"2026-07-05T06:43:08.770940+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTKIPACDRORQ","created_at":"2026-07-05T06:43:08.770940+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTKIPACDRORQAYY7","created_at":"2026-07-05T06:43:08.770940+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTKIPACD","created_at":"2026-07-05T06:43:08.770940+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/HTKIPACDRORQAYY7UJNMLQS2EM","json":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM.json","graph_json":"https://pith.science/api/pith-number/HTKIPACDRORQAYY7UJNMLQS2EM/graph.json","events_json":"https://pith.science/api/pith-number/HTKIPACDRORQAYY7UJNMLQS2EM/events.json","paper":"https://pith.science/paper/HTKIPACD"},"agent_actions":{"view_html":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM","download_json":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM.json","view_paper":"https://pith.science/paper/HTKIPACD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10408&json=true","fetch_graph":"https://pith.science/api/pith-number/HTKIPACDRORQAYY7UJNMLQS2EM/graph.json","fetch_events":"https://pith.science/api/pith-number/HTKIPACDRORQAYY7UJNMLQS2EM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM/action/storage_attestation","attest_author":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM/action/author_attestation","sign_citation":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM/action/citation_signature","submit_replication":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM/action/replication_record"}},"created_at":"2026-07-05T06:43:08.770940+00:00","updated_at":"2026-07-05T06:43:08.770940+00:00"}