{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AUN2EFX3J7SSYUKQLOFG4DZLML","short_pith_number":"pith:AUN2EFX3","schema_version":"1.0","canonical_sha256":"051ba216fb4fe52c51505b8a6e0f2b62d5f742405116a46a09dccee16bd590f2","source":{"kind":"arxiv","id":"2406.17758","version":3},"attestation_state":"computed","paper":{"title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Jianzong Wu, Kai Chen, Qianyu Zhou, Xiangtai Li, Yanhong Zeng, Yining Li, Yunhai Tong","submitted_at":"2024-06-25T17:42:25Z","abstract_excerpt":"In this work, we present MotionBooth, an innovative framework designed for animating customized subjects with precise control over both object and camera movements. By leveraging a few images of a specific object, we efficiently fine-tune a text-to-video model to capture the object's shape and attributes accurately. Our approach presents subject region loss and video preservation loss to enhance the subject's learning performance, along with a subject token cross-attention loss to integrate the customized subject with motion control signals. Additionally, we propose training-free techniques fo"},"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":"2406.17758","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T17:42:25Z","cross_cats_sorted":[],"title_canon_sha256":"50dfd0f5db7ad3fcae343a27a658b2b3c56c4ca6da68a8ecbfdbdd88048c1ca9","abstract_canon_sha256":"dd683e8f5d88c41bfbb2c8603bf32b05e0f9b0a310315650182afa53bded3272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:56.025477Z","signature_b64":"oSYhmviuQrNfWynsH1j3j6knUqx3ctLA/7L75xwgKAW262ZysA3ZslcVSTzy1CFqEVG+Ex2t7shJ9GuX0iKcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"051ba216fb4fe52c51505b8a6e0f2b62d5f742405116a46a09dccee16bd590f2","last_reissued_at":"2026-07-05T09:27:56.024842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:56.024842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Jianzong Wu, Kai Chen, Qianyu Zhou, Xiangtai Li, Yanhong Zeng, Yining Li, Yunhai Tong","submitted_at":"2024-06-25T17:42:25Z","abstract_excerpt":"In this work, we present MotionBooth, an innovative framework designed for animating customized subjects with precise control over both object and camera movements. By leveraging a few images of a specific object, we efficiently fine-tune a text-to-video model to capture the object's shape and attributes accurately. Our approach presents subject region loss and video preservation loss to enhance the subject's learning performance, along with a subject token cross-attention loss to integrate the customized subject with motion control signals. Additionally, we propose training-free techniques fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17758","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/2406.17758/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":"2406.17758","created_at":"2026-07-05T09:27:56.024948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17758v3","created_at":"2026-07-05T09:27:56.024948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17758","created_at":"2026-07-05T09:27:56.024948+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUN2EFX3J7SS","created_at":"2026-07-05T09:27:56.024948+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUN2EFX3J7SSYUKQ","created_at":"2026-07-05T09:27:56.024948+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUN2EFX3","created_at":"2026-07-05T09:27:56.024948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11783","citing_title":"A Comprehensive Ecosystem for Open-Domain Customized Video Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17816","citing_title":"Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23690","citing_title":"SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AUN2EFX3J7SSYUKQLOFG4DZLML","json":"https://pith.science/pith/AUN2EFX3J7SSYUKQLOFG4DZLML.json","graph_json":"https://pith.science/api/pith-number/AUN2EFX3J7SSYUKQLOFG4DZLML/graph.json","events_json":"https://pith.science/api/pith-number/AUN2EFX3J7SSYUKQLOFG4DZLML/events.json","paper":"https://pith.science/paper/AUN2EFX3"},"agent_actions":{"view_html":"https://pith.science/pith/AUN2EFX3J7SSYUKQLOFG4DZLML","download_json":"https://pith.science/pith/AUN2EFX3J7SSYUKQLOFG4DZLML.json","view_paper":"https://pith.science/paper/AUN2EFX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17758&json=true","fetch_graph":"https://pith.science/api/pith-number/AUN2EFX3J7SSYUKQLOFG4DZLML/graph.json","fetch_events":"https://pith.science/api/pith-number/AUN2EFX3J7SSYUKQLOFG4DZLML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUN2EFX3J7SSYUKQLOFG4DZLML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUN2EFX3J7SSYUKQLOFG4DZLML/action/storage_attestation","attest_author":"https://pith.science/pith/AUN2EFX3J7SSYUKQLOFG4DZLML/action/author_attestation","sign_citation":"https://pith.science/pith/AUN2EFX3J7SSYUKQLOFG4DZLML/action/citation_signature","submit_replication":"https://pith.science/pith/AUN2EFX3J7SSYUKQLOFG4DZLML/action/replication_record"}},"created_at":"2026-07-05T09:27:56.024948+00:00","updated_at":"2026-07-05T09:27:56.024948+00:00"}