{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G5MNK2IQXB6LNAJTE7ISSHK5SW","short_pith_number":"pith:G5MNK2IQ","schema_version":"1.0","canonical_sha256":"3758d56910b87cb6813327d1291d5d95984731e9981328b42ac8a8b58ac851ea","source":{"kind":"arxiv","id":"2303.02483","version":1},"attestation_state":"computed","paper":{"title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Licheng Yu, Li Zhang, Tao Xiang, Xiao Han, Xiatian Zhu, Yi-Zhe Song","submitted_at":"2023-03-04T19:07:48Z","abstract_excerpt":"In the fashion domain, there exists a variety of vision-and-language (V+L) tasks, including cross-modal retrieval, text-guided image retrieval, multi-modal classification, and image captioning. They differ drastically in each individual input/output format and dataset size. It has been common to design a task-specific model and fine-tune it independently from a pre-trained V+L model (e.g., CLIP). This results in parameter inefficiency and inability to exploit inter-task relatedness. To address such issues, we propose a novel FAshion-focused Multi-task Efficient learning method for Vision-and-L"},"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":"2303.02483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T19:07:48Z","cross_cats_sorted":[],"title_canon_sha256":"8677a5fced08e3a5f0ad72a10fb1157d585909decec6d38cab2d6f2f0d6a28cb","abstract_canon_sha256":"310ca68281416f369c5b3cee8a5d890b52e2439e0cf67136f61816ac39cc91ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:11.864969Z","signature_b64":"71mkzvU6QEv6Yn/OIGMMKqNgblzH35TRf3dQXE21KLkakpnTqbuCT0zZCkDwhzODrNFTzq2t7vPOcoX2AkPvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3758d56910b87cb6813327d1291d5d95984731e9981328b42ac8a8b58ac851ea","last_reissued_at":"2026-07-05T05:48:11.864621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:11.864621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Licheng Yu, Li Zhang, Tao Xiang, Xiao Han, Xiatian Zhu, Yi-Zhe Song","submitted_at":"2023-03-04T19:07:48Z","abstract_excerpt":"In the fashion domain, there exists a variety of vision-and-language (V+L) tasks, including cross-modal retrieval, text-guided image retrieval, multi-modal classification, and image captioning. They differ drastically in each individual input/output format and dataset size. It has been common to design a task-specific model and fine-tune it independently from a pre-trained V+L model (e.g., CLIP). This results in parameter inefficiency and inability to exploit inter-task relatedness. To address such issues, we propose a novel FAshion-focused Multi-task Efficient learning method for Vision-and-L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02483","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/2303.02483/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":"2303.02483","created_at":"2026-07-05T05:48:11.864683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02483v1","created_at":"2026-07-05T05:48:11.864683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02483","created_at":"2026-07-05T05:48:11.864683+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5MNK2IQXB6L","created_at":"2026-07-05T05:48:11.864683+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5MNK2IQXB6LNAJT","created_at":"2026-07-05T05:48:11.864683+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5MNK2IQ","created_at":"2026-07-05T05:48:11.864683+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/G5MNK2IQXB6LNAJTE7ISSHK5SW","json":"https://pith.science/pith/G5MNK2IQXB6LNAJTE7ISSHK5SW.json","graph_json":"https://pith.science/api/pith-number/G5MNK2IQXB6LNAJTE7ISSHK5SW/graph.json","events_json":"https://pith.science/api/pith-number/G5MNK2IQXB6LNAJTE7ISSHK5SW/events.json","paper":"https://pith.science/paper/G5MNK2IQ"},"agent_actions":{"view_html":"https://pith.science/pith/G5MNK2IQXB6LNAJTE7ISSHK5SW","download_json":"https://pith.science/pith/G5MNK2IQXB6LNAJTE7ISSHK5SW.json","view_paper":"https://pith.science/paper/G5MNK2IQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02483&json=true","fetch_graph":"https://pith.science/api/pith-number/G5MNK2IQXB6LNAJTE7ISSHK5SW/graph.json","fetch_events":"https://pith.science/api/pith-number/G5MNK2IQXB6LNAJTE7ISSHK5SW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5MNK2IQXB6LNAJTE7ISSHK5SW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5MNK2IQXB6LNAJTE7ISSHK5SW/action/storage_attestation","attest_author":"https://pith.science/pith/G5MNK2IQXB6LNAJTE7ISSHK5SW/action/author_attestation","sign_citation":"https://pith.science/pith/G5MNK2IQXB6LNAJTE7ISSHK5SW/action/citation_signature","submit_replication":"https://pith.science/pith/G5MNK2IQXB6LNAJTE7ISSHK5SW/action/replication_record"}},"created_at":"2026-07-05T05:48:11.864683+00:00","updated_at":"2026-07-05T05:48:11.864683+00:00"}