{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:POECXX4FZ54KQURUHSETQ4NFFF","short_pith_number":"pith:POECXX4F","schema_version":"1.0","canonical_sha256":"7b882bdf85cf78a852343c893871a52960886cd67d70ec2270bd60c3c0c1222a","source":{"kind":"arxiv","id":"2412.19997","version":2},"attestation_state":"computed","paper":{"title":"FashionFAE: Fine-grained Attributes Enhanced Fashion Vision-Language Pre-training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dehong Gao, Jiale Huang, Jinxia Zhang, Xin Wang, Yang Hu, Zechao Zhan","submitted_at":"2024-12-28T03:45:49Z","abstract_excerpt":"Large-scale Vision-Language Pre-training (VLP) has demonstrated remarkable success in the general domain. However, in the fashion domain, items are distinguished by fine-grained attributes like texture and material, which are crucial for tasks such as retrieval. Existing models often fail to leverage these fine-grained attributes from both text and image modalities. To address the above issues, we propose a novel approach for the fashion domain, Fine-grained Attributes Enhanced VLP (FashionFAE), which focuses on the detailed characteristics of fashion data. An attribute-emphasized text predict"},"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":"2412.19997","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-28T03:45:49Z","cross_cats_sorted":[],"title_canon_sha256":"1a64b615f4676a1c3fb0fd26a00095cebc09d72048ce17669cea3e9ac91e0982","abstract_canon_sha256":"4a533759ec612c36ecf5e064013b3ff1ccf49e14b2c9cfb7e2c7affc001878e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:58.029938Z","signature_b64":"zCTZZiyFmZ77T96S0IFQ1+CXD7lzSkZGDB066dVHbj3VRDErj7sN5kDdSlCCXXI9mwSX0l0YzF8z5hl7qXrgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b882bdf85cf78a852343c893871a52960886cd67d70ec2270bd60c3c0c1222a","last_reissued_at":"2026-07-05T09:59:58.029491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:58.029491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FashionFAE: Fine-grained Attributes Enhanced Fashion Vision-Language Pre-training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dehong Gao, Jiale Huang, Jinxia Zhang, Xin Wang, Yang Hu, Zechao Zhan","submitted_at":"2024-12-28T03:45:49Z","abstract_excerpt":"Large-scale Vision-Language Pre-training (VLP) has demonstrated remarkable success in the general domain. However, in the fashion domain, items are distinguished by fine-grained attributes like texture and material, which are crucial for tasks such as retrieval. Existing models often fail to leverage these fine-grained attributes from both text and image modalities. To address the above issues, we propose a novel approach for the fashion domain, Fine-grained Attributes Enhanced VLP (FashionFAE), which focuses on the detailed characteristics of fashion data. An attribute-emphasized text predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19997","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/2412.19997/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":"2412.19997","created_at":"2026-07-05T09:59:58.029549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19997v2","created_at":"2026-07-05T09:59:58.029549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19997","created_at":"2026-07-05T09:59:58.029549+00:00"},{"alias_kind":"pith_short_12","alias_value":"POECXX4FZ54K","created_at":"2026-07-05T09:59:58.029549+00:00"},{"alias_kind":"pith_short_16","alias_value":"POECXX4FZ54KQURU","created_at":"2026-07-05T09:59:58.029549+00:00"},{"alias_kind":"pith_short_8","alias_value":"POECXX4F","created_at":"2026-07-05T09:59:58.029549+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/POECXX4FZ54KQURUHSETQ4NFFF","json":"https://pith.science/pith/POECXX4FZ54KQURUHSETQ4NFFF.json","graph_json":"https://pith.science/api/pith-number/POECXX4FZ54KQURUHSETQ4NFFF/graph.json","events_json":"https://pith.science/api/pith-number/POECXX4FZ54KQURUHSETQ4NFFF/events.json","paper":"https://pith.science/paper/POECXX4F"},"agent_actions":{"view_html":"https://pith.science/pith/POECXX4FZ54KQURUHSETQ4NFFF","download_json":"https://pith.science/pith/POECXX4FZ54KQURUHSETQ4NFFF.json","view_paper":"https://pith.science/paper/POECXX4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19997&json=true","fetch_graph":"https://pith.science/api/pith-number/POECXX4FZ54KQURUHSETQ4NFFF/graph.json","fetch_events":"https://pith.science/api/pith-number/POECXX4FZ54KQURUHSETQ4NFFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POECXX4FZ54KQURUHSETQ4NFFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POECXX4FZ54KQURUHSETQ4NFFF/action/storage_attestation","attest_author":"https://pith.science/pith/POECXX4FZ54KQURUHSETQ4NFFF/action/author_attestation","sign_citation":"https://pith.science/pith/POECXX4FZ54KQURUHSETQ4NFFF/action/citation_signature","submit_replication":"https://pith.science/pith/POECXX4FZ54KQURUHSETQ4NFFF/action/replication_record"}},"created_at":"2026-07-05T09:59:58.029549+00:00","updated_at":"2026-07-05T09:59:58.029549+00:00"}