{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E7MKMKWVMEDGLWELI6VQNYYR2E","short_pith_number":"pith:E7MKMKWV","schema_version":"1.0","canonical_sha256":"27d8a62ad5610665d88b47ab06e311d11c85848489f6df6e6f4b3d0c932112fc","source":{"kind":"arxiv","id":"2503.21781","version":1},"attestation_state":"computed","paper":{"title":"VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Pin Huang, Fu-En Yang, Hung-Kai Chung, Kai-Po Chang, Yen-Siang Wu, Yu-Chiang Frank Wang","submitted_at":"2025-03-27T17:59:58Z","abstract_excerpt":"Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focus on personalizing a single concept, either subject identity or motion pattern, limiting their effectiveness for multiple subjects with the desired motion patterns. To tackle this challenge, we propose a unified framework VideoMage for video customization over both multiple subjects and their interactive motions. VideoMage employs subject and motion LoRAs to capture personalized content from user-provided images and "},"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":"2503.21781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"54d5c16773a0fdb82b646507100a2339a87e67a04b90f08d293ca99fae8779ab","abstract_canon_sha256":"ae25221d3d683a1a7bdbdfab4201d69ee07b237588d1b676e7bd52764bc35e22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:30.665883Z","signature_b64":"vBEPvJzcAAkhARp99zJAEHmso47d9ODIV7RTbXAeh8jigT2/6dIpqwSQsaW2AC8Aob+/wnn2aPitiqKcHHU1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27d8a62ad5610665d88b47ab06e311d11c85848489f6df6e6f4b3d0c932112fc","last_reissued_at":"2026-07-05T10:40:30.665396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:30.665396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Pin Huang, Fu-En Yang, Hung-Kai Chung, Kai-Po Chang, Yen-Siang Wu, Yu-Chiang Frank Wang","submitted_at":"2025-03-27T17:59:58Z","abstract_excerpt":"Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focus on personalizing a single concept, either subject identity or motion pattern, limiting their effectiveness for multiple subjects with the desired motion patterns. To tackle this challenge, we propose a unified framework VideoMage for video customization over both multiple subjects and their interactive motions. VideoMage employs subject and motion LoRAs to capture personalized content from user-provided images and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21781","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/2503.21781/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":"2503.21781","created_at":"2026-07-05T10:40:30.665458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21781v1","created_at":"2026-07-05T10:40:30.665458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21781","created_at":"2026-07-05T10:40:30.665458+00:00"},{"alias_kind":"pith_short_12","alias_value":"E7MKMKWVMEDG","created_at":"2026-07-05T10:40:30.665458+00:00"},{"alias_kind":"pith_short_16","alias_value":"E7MKMKWVMEDGLWEL","created_at":"2026-07-05T10:40:30.665458+00:00"},{"alias_kind":"pith_short_8","alias_value":"E7MKMKWV","created_at":"2026-07-05T10:40:30.665458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11244","citing_title":"Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E7MKMKWVMEDGLWELI6VQNYYR2E","json":"https://pith.science/pith/E7MKMKWVMEDGLWELI6VQNYYR2E.json","graph_json":"https://pith.science/api/pith-number/E7MKMKWVMEDGLWELI6VQNYYR2E/graph.json","events_json":"https://pith.science/api/pith-number/E7MKMKWVMEDGLWELI6VQNYYR2E/events.json","paper":"https://pith.science/paper/E7MKMKWV"},"agent_actions":{"view_html":"https://pith.science/pith/E7MKMKWVMEDGLWELI6VQNYYR2E","download_json":"https://pith.science/pith/E7MKMKWVMEDGLWELI6VQNYYR2E.json","view_paper":"https://pith.science/paper/E7MKMKWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21781&json=true","fetch_graph":"https://pith.science/api/pith-number/E7MKMKWVMEDGLWELI6VQNYYR2E/graph.json","fetch_events":"https://pith.science/api/pith-number/E7MKMKWVMEDGLWELI6VQNYYR2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E7MKMKWVMEDGLWELI6VQNYYR2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E7MKMKWVMEDGLWELI6VQNYYR2E/action/storage_attestation","attest_author":"https://pith.science/pith/E7MKMKWVMEDGLWELI6VQNYYR2E/action/author_attestation","sign_citation":"https://pith.science/pith/E7MKMKWVMEDGLWELI6VQNYYR2E/action/citation_signature","submit_replication":"https://pith.science/pith/E7MKMKWVMEDGLWELI6VQNYYR2E/action/replication_record"}},"created_at":"2026-07-05T10:40:30.665458+00:00","updated_at":"2026-07-05T10:40:30.665458+00:00"}