{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WTRUD3MWSBBXH43XPGNMHNVRVL","short_pith_number":"pith:WTRUD3MW","schema_version":"1.0","canonical_sha256":"b4e341ed96904373f377799ac3b6b1aafb14be805484df8d73f0fbb1acb67c03","source":{"kind":"arxiv","id":"2412.05275","version":1},"attestation_state":"computed","paper":{"title":"MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Connor Dunlop, Hidir Yesiltepe, Pinar Yanardag, Tuna Han Salih Meral","submitted_at":"2024-12-06T18:59:12Z","abstract_excerpt":"Text-to-video models have demonstrated impressive capabilities in producing diverse and captivating video content, showcasing a notable advancement in generative AI. However, these models generally lack fine-grained control over motion patterns, limiting their practical applicability. We introduce MotionFlow, a novel framework designed for motion transfer in video diffusion models. Our method utilizes cross-attention maps to accurately capture and manipulate spatial and temporal dynamics, enabling seamless motion transfers across various contexts. Our approach does not require training and wor"},"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":"2412.05275","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T18:59:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"322d06d3f73255581957dedc13ecd876c17d2c4919fa2ea8d3cd189b87e93980","abstract_canon_sha256":"82249bac09f609c46114b227ee7e94f35f96749d79f90139d86d02d1601c7074"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:35.755199Z","signature_b64":"Y6CF//0vrrlRfWFv6RmpWPt9Z6RgufyJiqyylBJIbuGrL1yOyV0qeqh/18gjjllHZPKyblbIN4C8P7rN5jmxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4e341ed96904373f377799ac3b6b1aafb14be805484df8d73f0fbb1acb67c03","last_reissued_at":"2026-07-05T09:45:35.754733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:35.754733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Connor Dunlop, Hidir Yesiltepe, Pinar Yanardag, Tuna Han Salih Meral","submitted_at":"2024-12-06T18:59:12Z","abstract_excerpt":"Text-to-video models have demonstrated impressive capabilities in producing diverse and captivating video content, showcasing a notable advancement in generative AI. However, these models generally lack fine-grained control over motion patterns, limiting their practical applicability. We introduce MotionFlow, a novel framework designed for motion transfer in video diffusion models. Our method utilizes cross-attention maps to accurately capture and manipulate spatial and temporal dynamics, enabling seamless motion transfers across various contexts. Our approach does not require training and wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05275","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/2412.05275/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":"2412.05275","created_at":"2026-07-05T09:45:35.754798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05275v1","created_at":"2026-07-05T09:45:35.754798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05275","created_at":"2026-07-05T09:45:35.754798+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTRUD3MWSBBX","created_at":"2026-07-05T09:45:35.754798+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTRUD3MWSBBXH43X","created_at":"2026-07-05T09:45:35.754798+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTRUD3MW","created_at":"2026-07-05T09:45:35.754798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22996","citing_title":"CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23690","citing_title":"SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10030","citing_title":"Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WTRUD3MWSBBXH43XPGNMHNVRVL","json":"https://pith.science/pith/WTRUD3MWSBBXH43XPGNMHNVRVL.json","graph_json":"https://pith.science/api/pith-number/WTRUD3MWSBBXH43XPGNMHNVRVL/graph.json","events_json":"https://pith.science/api/pith-number/WTRUD3MWSBBXH43XPGNMHNVRVL/events.json","paper":"https://pith.science/paper/WTRUD3MW"},"agent_actions":{"view_html":"https://pith.science/pith/WTRUD3MWSBBXH43XPGNMHNVRVL","download_json":"https://pith.science/pith/WTRUD3MWSBBXH43XPGNMHNVRVL.json","view_paper":"https://pith.science/paper/WTRUD3MW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05275&json=true","fetch_graph":"https://pith.science/api/pith-number/WTRUD3MWSBBXH43XPGNMHNVRVL/graph.json","fetch_events":"https://pith.science/api/pith-number/WTRUD3MWSBBXH43XPGNMHNVRVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTRUD3MWSBBXH43XPGNMHNVRVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTRUD3MWSBBXH43XPGNMHNVRVL/action/storage_attestation","attest_author":"https://pith.science/pith/WTRUD3MWSBBXH43XPGNMHNVRVL/action/author_attestation","sign_citation":"https://pith.science/pith/WTRUD3MWSBBXH43XPGNMHNVRVL/action/citation_signature","submit_replication":"https://pith.science/pith/WTRUD3MWSBBXH43XPGNMHNVRVL/action/replication_record"}},"created_at":"2026-07-05T09:45:35.754798+00:00","updated_at":"2026-07-05T09:45:35.754798+00:00"}