{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5LQ674WEQVGP5YHUTT3JHMWIRF","short_pith_number":"pith:5LQ674WE","schema_version":"1.0","canonical_sha256":"eae1eff2c4854cfee0f49cf693b2c889473364f795cd6613a64a73039aa5d9f1","source":{"kind":"arxiv","id":"2204.00298","version":4},"attestation_state":"computed","paper":{"title":"Unitail: Detecting, Reading, and Matching in Retail Scene","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenchen Zhu, Fangyi Chen, Han Zhang, Hao Chen, Jiachen Dou, Marios Savvides, Shentong Mo, Uzair Ahmed, Yongxin Zhang, Zaiwang Li","submitted_at":"2022-04-01T09:06:48Z","abstract_excerpt":"To make full use of computer vision technology in stores, it is required to consider the actual needs that fit the characteristics of the retail scene. Pursuing this goal, we introduce the United Retail Datasets (Unitail), a large-scale benchmark of basic visual tasks on products that challenges algorithms for detecting, reading, and matching. With 1.8M quadrilateral-shaped instances annotated, the Unitail offers a detection dataset to align product appearance better. Furthermore, it provides a gallery-style OCR dataset containing 1454 product categories, 30k text regions, and 21k transcriptio"},"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":"2204.00298","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-01T09:06:48Z","cross_cats_sorted":[],"title_canon_sha256":"64df3289e3c2ad5e2177cf824a72f5b27c54276838f512c27868ebbe87712a4c","abstract_canon_sha256":"e0a6d6fd31eaec3a2df253096399db8a5cacc3dbe39fc56aec617ad35c69323b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:55.338904Z","signature_b64":"VFnbqXwD/Tr1+592/fsrlQB/TYI8+7hxVZ1YXChu7y3o6xexRBk1xm33qOZpsLl6J3nugN2T97268hAhjaYZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eae1eff2c4854cfee0f49cf693b2c889473364f795cd6613a64a73039aa5d9f1","last_reissued_at":"2026-07-05T04:41:55.338381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:55.338381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unitail: Detecting, Reading, and Matching in Retail Scene","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenchen Zhu, Fangyi Chen, Han Zhang, Hao Chen, Jiachen Dou, Marios Savvides, Shentong Mo, Uzair Ahmed, Yongxin Zhang, Zaiwang Li","submitted_at":"2022-04-01T09:06:48Z","abstract_excerpt":"To make full use of computer vision technology in stores, it is required to consider the actual needs that fit the characteristics of the retail scene. Pursuing this goal, we introduce the United Retail Datasets (Unitail), a large-scale benchmark of basic visual tasks on products that challenges algorithms for detecting, reading, and matching. With 1.8M quadrilateral-shaped instances annotated, the Unitail offers a detection dataset to align product appearance better. Furthermore, it provides a gallery-style OCR dataset containing 1454 product categories, 30k text regions, and 21k transcriptio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00298","kind":"arxiv","version":4},"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/2204.00298/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":"2204.00298","created_at":"2026-07-05T04:41:55.338461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.00298v4","created_at":"2026-07-05T04:41:55.338461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00298","created_at":"2026-07-05T04:41:55.338461+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LQ674WEQVGP","created_at":"2026-07-05T04:41:55.338461+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LQ674WEQVGP5YHU","created_at":"2026-07-05T04:41:55.338461+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LQ674WE","created_at":"2026-07-05T04:41:55.338461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10591","citing_title":"Creation and Evaluation of a Food Product Image Dataset for Product Property Extraction","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LQ674WEQVGP5YHUTT3JHMWIRF","json":"https://pith.science/pith/5LQ674WEQVGP5YHUTT3JHMWIRF.json","graph_json":"https://pith.science/api/pith-number/5LQ674WEQVGP5YHUTT3JHMWIRF/graph.json","events_json":"https://pith.science/api/pith-number/5LQ674WEQVGP5YHUTT3JHMWIRF/events.json","paper":"https://pith.science/paper/5LQ674WE"},"agent_actions":{"view_html":"https://pith.science/pith/5LQ674WEQVGP5YHUTT3JHMWIRF","download_json":"https://pith.science/pith/5LQ674WEQVGP5YHUTT3JHMWIRF.json","view_paper":"https://pith.science/paper/5LQ674WE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.00298&json=true","fetch_graph":"https://pith.science/api/pith-number/5LQ674WEQVGP5YHUTT3JHMWIRF/graph.json","fetch_events":"https://pith.science/api/pith-number/5LQ674WEQVGP5YHUTT3JHMWIRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LQ674WEQVGP5YHUTT3JHMWIRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LQ674WEQVGP5YHUTT3JHMWIRF/action/storage_attestation","attest_author":"https://pith.science/pith/5LQ674WEQVGP5YHUTT3JHMWIRF/action/author_attestation","sign_citation":"https://pith.science/pith/5LQ674WEQVGP5YHUTT3JHMWIRF/action/citation_signature","submit_replication":"https://pith.science/pith/5LQ674WEQVGP5YHUTT3JHMWIRF/action/replication_record"}},"created_at":"2026-07-05T04:41:55.338461+00:00","updated_at":"2026-07-05T04:41:55.338461+00:00"}