{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YPQL3SYIHV4HCRT2QRTOJNVAZQ","short_pith_number":"pith:YPQL3SYI","schema_version":"1.0","canonical_sha256":"c3e0bdcb083d7871467a8466e4b6a0cc219b8a53a7388ec62be28e7f487f558b","source":{"kind":"arxiv","id":"2103.16110","version":3},"attestation_state":"computed","paper":{"title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ben Chen, Dehong Gao, Deng-Ping Fan, Haoming Zhou, Linbo Jin, Ling Shao, Mingchen Zhuge, Minghui Qiu","submitted_at":"2021-03-30T06:53:00Z","abstract_excerpt":"We present a new vision-language (VL) pre-training model dubbed Kaleido-BERT, which introduces a novel kaleido strategy for fashion cross-modality representations from transformers. In contrast to random masking strategy of recent VL models, we design alignment guided masking to jointly focus more on image-text semantic relations. To this end, we carry out five novel tasks, i.e., rotation, jigsaw, camouflage, grey-to-color, and blank-to-color for self-supervised VL pre-training at patches of different scale. Kaleido-BERT is conceptually simple and easy to extend to the existing BERT framework,"},"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":"2103.16110","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T06:53:00Z","cross_cats_sorted":[],"title_canon_sha256":"bde37ebb0839402a1c30d3330c7fc0345b37e28e63870211fe6ace10673cfbf5","abstract_canon_sha256":"819fd4e8442df1a1dae2ebe10ac27f0fa22cf3933735b75190b2bda80c7773c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:16.799230Z","signature_b64":"Q6u70pUBJ+/YfOUfiiapguOfpKngPItdgJs5UIjux6BcfYQqQbvtzaPYWUnrgWNpRcadzoUbvNvk0bKrgOOsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3e0bdcb083d7871467a8466e4b6a0cc219b8a53a7388ec62be28e7f487f558b","last_reissued_at":"2026-07-05T02:32:16.798813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:16.798813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ben Chen, Dehong Gao, Deng-Ping Fan, Haoming Zhou, Linbo Jin, Ling Shao, Mingchen Zhuge, Minghui Qiu","submitted_at":"2021-03-30T06:53:00Z","abstract_excerpt":"We present a new vision-language (VL) pre-training model dubbed Kaleido-BERT, which introduces a novel kaleido strategy for fashion cross-modality representations from transformers. In contrast to random masking strategy of recent VL models, we design alignment guided masking to jointly focus more on image-text semantic relations. To this end, we carry out five novel tasks, i.e., rotation, jigsaw, camouflage, grey-to-color, and blank-to-color for self-supervised VL pre-training at patches of different scale. Kaleido-BERT is conceptually simple and easy to extend to the existing BERT framework,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16110","kind":"arxiv","version":3},"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/2103.16110/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":"2103.16110","created_at":"2026-07-05T02:32:16.798875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.16110v3","created_at":"2026-07-05T02:32:16.798875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16110","created_at":"2026-07-05T02:32:16.798875+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPQL3SYIHV4H","created_at":"2026-07-05T02:32:16.798875+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPQL3SYIHV4HCRT2","created_at":"2026-07-05T02:32:16.798875+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPQL3SYI","created_at":"2026-07-05T02:32:16.798875+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/YPQL3SYIHV4HCRT2QRTOJNVAZQ","json":"https://pith.science/pith/YPQL3SYIHV4HCRT2QRTOJNVAZQ.json","graph_json":"https://pith.science/api/pith-number/YPQL3SYIHV4HCRT2QRTOJNVAZQ/graph.json","events_json":"https://pith.science/api/pith-number/YPQL3SYIHV4HCRT2QRTOJNVAZQ/events.json","paper":"https://pith.science/paper/YPQL3SYI"},"agent_actions":{"view_html":"https://pith.science/pith/YPQL3SYIHV4HCRT2QRTOJNVAZQ","download_json":"https://pith.science/pith/YPQL3SYIHV4HCRT2QRTOJNVAZQ.json","view_paper":"https://pith.science/paper/YPQL3SYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.16110&json=true","fetch_graph":"https://pith.science/api/pith-number/YPQL3SYIHV4HCRT2QRTOJNVAZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YPQL3SYIHV4HCRT2QRTOJNVAZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPQL3SYIHV4HCRT2QRTOJNVAZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPQL3SYIHV4HCRT2QRTOJNVAZQ/action/storage_attestation","attest_author":"https://pith.science/pith/YPQL3SYIHV4HCRT2QRTOJNVAZQ/action/author_attestation","sign_citation":"https://pith.science/pith/YPQL3SYIHV4HCRT2QRTOJNVAZQ/action/citation_signature","submit_replication":"https://pith.science/pith/YPQL3SYIHV4HCRT2QRTOJNVAZQ/action/replication_record"}},"created_at":"2026-07-05T02:32:16.798875+00:00","updated_at":"2026-07-05T02:32:16.798875+00:00"}