{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TW5ZZK5MKZKWQMLECDLDRK7SGI","short_pith_number":"pith:TW5ZZK5M","schema_version":"1.0","canonical_sha256":"9dbb9cabac565568316410d638abf2323acf8614dc634d3f5ee939bc74b67b9c","source":{"kind":"arxiv","id":"2410.13830","version":1},"attestation_state":"computed","paper":{"title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Liu, Hangjie Yuan, Haonan Qiu, Hongming Shan, Jiaxin Ye, Rui Zhao, Shiwei Zhang, Xiang Wang, Yingya Zhang, Yujie Wei, Yutong Feng, Zhizhong Huang","submitted_at":"2024-10-17T17:52:57Z","abstract_excerpt":"Recent advances in customized video generation have enabled users to create videos tailored to both specific subjects and motion trajectories. However, existing methods often require complicated test-time fine-tuning and struggle with balancing subject learning and motion control, limiting their real-world applications. In this paper, we present DreamVideo-2, a zero-shot video customization framework capable of generating videos with a specific subject and motion trajectory, guided by a single image and a bounding box sequence, respectively, and without the need for test-time fine-tuning. Spec"},"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":"2410.13830","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T17:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"718ee641de06228e4d7f6ff8a97eb857d575ab5af1b5e093080628ff7713104f","abstract_canon_sha256":"13725a9db6e9a1c02cc88e94b8526480c39bdfcb18296613e33f822ac72514c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:06.302231Z","signature_b64":"SQNf5++EbSGFLyzrT8MRy5GfyVr7FgYHOPyQuWQghGGLWL5shMR3RuMRzv9HTF6RBvJb7g7btTTy96hRt3PbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dbb9cabac565568316410d638abf2323acf8614dc634d3f5ee939bc74b67b9c","last_reissued_at":"2026-07-05T09:22:06.301740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:06.301740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Liu, Hangjie Yuan, Haonan Qiu, Hongming Shan, Jiaxin Ye, Rui Zhao, Shiwei Zhang, Xiang Wang, Yingya Zhang, Yujie Wei, Yutong Feng, Zhizhong Huang","submitted_at":"2024-10-17T17:52:57Z","abstract_excerpt":"Recent advances in customized video generation have enabled users to create videos tailored to both specific subjects and motion trajectories. However, existing methods often require complicated test-time fine-tuning and struggle with balancing subject learning and motion control, limiting their real-world applications. In this paper, we present DreamVideo-2, a zero-shot video customization framework capable of generating videos with a specific subject and motion trajectory, guided by a single image and a bounding box sequence, respectively, and without the need for test-time fine-tuning. Spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13830","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/2410.13830/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":"2410.13830","created_at":"2026-07-05T09:22:06.301801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13830v1","created_at":"2026-07-05T09:22:06.301801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13830","created_at":"2026-07-05T09:22:06.301801+00:00"},{"alias_kind":"pith_short_12","alias_value":"TW5ZZK5MKZKW","created_at":"2026-07-05T09:22:06.301801+00:00"},{"alias_kind":"pith_short_16","alias_value":"TW5ZZK5MKZKWQMLE","created_at":"2026-07-05T09:22:06.301801+00:00"},{"alias_kind":"pith_short_8","alias_value":"TW5ZZK5M","created_at":"2026-07-05T09:22:06.301801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11783","citing_title":"A Comprehensive Ecosystem for Open-Domain Customized Video Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17816","citing_title":"Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09646","citing_title":"VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07598","citing_title":"VACE: All-in-One Video Creation and Editing","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14569","citing_title":"Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":184,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15923","citing_title":"Hierarchical Codec Diffusion for Video-to-Speech Generation","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TW5ZZK5MKZKWQMLECDLDRK7SGI","json":"https://pith.science/pith/TW5ZZK5MKZKWQMLECDLDRK7SGI.json","graph_json":"https://pith.science/api/pith-number/TW5ZZK5MKZKWQMLECDLDRK7SGI/graph.json","events_json":"https://pith.science/api/pith-number/TW5ZZK5MKZKWQMLECDLDRK7SGI/events.json","paper":"https://pith.science/paper/TW5ZZK5M"},"agent_actions":{"view_html":"https://pith.science/pith/TW5ZZK5MKZKWQMLECDLDRK7SGI","download_json":"https://pith.science/pith/TW5ZZK5MKZKWQMLECDLDRK7SGI.json","view_paper":"https://pith.science/paper/TW5ZZK5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13830&json=true","fetch_graph":"https://pith.science/api/pith-number/TW5ZZK5MKZKWQMLECDLDRK7SGI/graph.json","fetch_events":"https://pith.science/api/pith-number/TW5ZZK5MKZKWQMLECDLDRK7SGI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TW5ZZK5MKZKWQMLECDLDRK7SGI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TW5ZZK5MKZKWQMLECDLDRK7SGI/action/storage_attestation","attest_author":"https://pith.science/pith/TW5ZZK5MKZKWQMLECDLDRK7SGI/action/author_attestation","sign_citation":"https://pith.science/pith/TW5ZZK5MKZKWQMLECDLDRK7SGI/action/citation_signature","submit_replication":"https://pith.science/pith/TW5ZZK5MKZKWQMLECDLDRK7SGI/action/replication_record"}},"created_at":"2026-07-05T09:22:06.301801+00:00","updated_at":"2026-07-05T09:22:06.301801+00:00"}