{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WQ7ETN46TQD4CFN6HMMJCR4IMV","short_pith_number":"pith:WQ7ETN46","schema_version":"1.0","canonical_sha256":"b43e49b79e9c07c115be3b18914788656f01495999ae6ebe546f529e70fd3913","source":{"kind":"arxiv","id":"2412.07776","version":2},"attestation_state":"computed","paper":{"title":"Video Motion Transfer with Diffusion Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Pondaven, Aliaksandr Siarohin, Fabio Pizzati, Philip Torr, Sergey Tulyakov","submitted_at":"2024-12-10T18:59:58Z","abstract_excerpt":"We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one, designed specifically for Diffusion Transformers (DiT). We first process the reference video with a pre-trained DiT to analyze cross-frame attention maps and extract a patch-wise motion signal called the Attention Motion Flow (AMF). We guide the latent denoising process in an optimization-based, training-free, manner by optimizing latents with our AMF loss to generate videos reproducing the motion of the reference one. We also apply our optimization strategy to transformer positional embed"},"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":"2412.07776","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:59:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4eef10ed92d9f9fe46d436d3c71cb590c3b9c6cf0228bcdc9e3fc28fb5b5d440","abstract_canon_sha256":"87c2e0577f971bc0e4f25493f50e3b0a442b85cb6b37e6adec23ad6577034d07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:15.131880Z","signature_b64":"6bY5PWNiaGsNzMpLSVdIrrTlnjktSf6hUQkwXsEmGayLT1TpvMfb689QCdlPYPN0zxLboPxOcZ9HZnskE6eOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b43e49b79e9c07c115be3b18914788656f01495999ae6ebe546f529e70fd3913","last_reissued_at":"2026-07-05T10:40:15.131353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:15.131353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Motion Transfer with Diffusion Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Pondaven, Aliaksandr Siarohin, Fabio Pizzati, Philip Torr, Sergey Tulyakov","submitted_at":"2024-12-10T18:59:58Z","abstract_excerpt":"We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one, designed specifically for Diffusion Transformers (DiT). We first process the reference video with a pre-trained DiT to analyze cross-frame attention maps and extract a patch-wise motion signal called the Attention Motion Flow (AMF). We guide the latent denoising process in an optimization-based, training-free, manner by optimizing latents with our AMF loss to generate videos reproducing the motion of the reference one. We also apply our optimization strategy to transformer positional embed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07776","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/2412.07776/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":"2412.07776","created_at":"2026-07-05T10:40:15.131421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07776v2","created_at":"2026-07-05T10:40:15.131421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07776","created_at":"2026-07-05T10:40:15.131421+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQ7ETN46TQD4","created_at":"2026-07-05T10:40:15.131421+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQ7ETN46TQD4CFN6","created_at":"2026-07-05T10:40:15.131421+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQ7ETN46","created_at":"2026-07-05T10:40:15.131421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14167","citing_title":"LMP: Leveraging Motion Prior in Zero-Shot Video Generation with Diffusion Transformer","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQ7ETN46TQD4CFN6HMMJCR4IMV","json":"https://pith.science/pith/WQ7ETN46TQD4CFN6HMMJCR4IMV.json","graph_json":"https://pith.science/api/pith-number/WQ7ETN46TQD4CFN6HMMJCR4IMV/graph.json","events_json":"https://pith.science/api/pith-number/WQ7ETN46TQD4CFN6HMMJCR4IMV/events.json","paper":"https://pith.science/paper/WQ7ETN46"},"agent_actions":{"view_html":"https://pith.science/pith/WQ7ETN46TQD4CFN6HMMJCR4IMV","download_json":"https://pith.science/pith/WQ7ETN46TQD4CFN6HMMJCR4IMV.json","view_paper":"https://pith.science/paper/WQ7ETN46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07776&json=true","fetch_graph":"https://pith.science/api/pith-number/WQ7ETN46TQD4CFN6HMMJCR4IMV/graph.json","fetch_events":"https://pith.science/api/pith-number/WQ7ETN46TQD4CFN6HMMJCR4IMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQ7ETN46TQD4CFN6HMMJCR4IMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQ7ETN46TQD4CFN6HMMJCR4IMV/action/storage_attestation","attest_author":"https://pith.science/pith/WQ7ETN46TQD4CFN6HMMJCR4IMV/action/author_attestation","sign_citation":"https://pith.science/pith/WQ7ETN46TQD4CFN6HMMJCR4IMV/action/citation_signature","submit_replication":"https://pith.science/pith/WQ7ETN46TQD4CFN6HMMJCR4IMV/action/replication_record"}},"created_at":"2026-07-05T10:40:15.131421+00:00","updated_at":"2026-07-05T10:40:15.131421+00:00"}