{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:752Y6NLBZDJLJ3XGVKZYEXLS2K","short_pith_number":"pith:752Y6NLB","schema_version":"1.0","canonical_sha256":"ff758f3561c8d2b4eee6aab3825d72d2beb54a1f6c80a3ac37860bc882700336","source":{"kind":"arxiv","id":"2412.13185","version":1},"attestation_state":"computed","paper":{"title":"Move-in-2D: 2D-Conditioned Human Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Difan Liu, Feng Liu, Hsin-Ping Huang, Jui-Hsien Wang, Ming-Hsuan Yang, Yang Zhou, Zhan Xu","submitted_at":"2024-12-17T18:58:07Z","abstract_excerpt":"Generating realistic human videos remains a challenging task, with the most effective methods currently relying on a human motion sequence as a control signal. Existing approaches often use existing motion extracted from other videos, which restricts applications to specific motion types and global scene matching. We propose Move-in-2D, a novel approach to generate human motion sequences conditioned on a scene image, allowing for diverse motion that adapts to different scenes. Our approach utilizes a diffusion model that accepts both a scene image and text prompt as inputs, producing a motion "},"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":"2412.13185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T18:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"5423af00fe008258c6104e71210a6d1987e7886b9e337b9546ced68cc28d5240","abstract_canon_sha256":"c01e404e889e8d347387f9b24e041f2beaf1c12eb554fe24eae1c464e6987b13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:41.474104Z","signature_b64":"WV3L6wdsM2l6blo+hvHri6LPLk4Mc77tOjmu17BUzOxBZ5aBe2V1c10IVyaf68ZvZmJ2XuB4aSdNYaBDowzsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff758f3561c8d2b4eee6aab3825d72d2beb54a1f6c80a3ac37860bc882700336","last_reissued_at":"2026-07-05T09:50:41.473571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:41.473571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Move-in-2D: 2D-Conditioned Human Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Difan Liu, Feng Liu, Hsin-Ping Huang, Jui-Hsien Wang, Ming-Hsuan Yang, Yang Zhou, Zhan Xu","submitted_at":"2024-12-17T18:58:07Z","abstract_excerpt":"Generating realistic human videos remains a challenging task, with the most effective methods currently relying on a human motion sequence as a control signal. Existing approaches often use existing motion extracted from other videos, which restricts applications to specific motion types and global scene matching. We propose Move-in-2D, a novel approach to generate human motion sequences conditioned on a scene image, allowing for diverse motion that adapts to different scenes. Our approach utilizes a diffusion model that accepts both a scene image and text prompt as inputs, producing a motion "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13185","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/2412.13185/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":"2412.13185","created_at":"2026-07-05T09:50:41.473638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13185v1","created_at":"2026-07-05T09:50:41.473638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13185","created_at":"2026-07-05T09:50:41.473638+00:00"},{"alias_kind":"pith_short_12","alias_value":"752Y6NLBZDJL","created_at":"2026-07-05T09:50:41.473638+00:00"},{"alias_kind":"pith_short_16","alias_value":"752Y6NLBZDJLJ3XG","created_at":"2026-07-05T09:50:41.473638+00:00"},{"alias_kind":"pith_short_8","alias_value":"752Y6NLB","created_at":"2026-07-05T09:50:41.473638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/752Y6NLBZDJLJ3XGVKZYEXLS2K","json":"https://pith.science/pith/752Y6NLBZDJLJ3XGVKZYEXLS2K.json","graph_json":"https://pith.science/api/pith-number/752Y6NLBZDJLJ3XGVKZYEXLS2K/graph.json","events_json":"https://pith.science/api/pith-number/752Y6NLBZDJLJ3XGVKZYEXLS2K/events.json","paper":"https://pith.science/paper/752Y6NLB"},"agent_actions":{"view_html":"https://pith.science/pith/752Y6NLBZDJLJ3XGVKZYEXLS2K","download_json":"https://pith.science/pith/752Y6NLBZDJLJ3XGVKZYEXLS2K.json","view_paper":"https://pith.science/paper/752Y6NLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13185&json=true","fetch_graph":"https://pith.science/api/pith-number/752Y6NLBZDJLJ3XGVKZYEXLS2K/graph.json","fetch_events":"https://pith.science/api/pith-number/752Y6NLBZDJLJ3XGVKZYEXLS2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/752Y6NLBZDJLJ3XGVKZYEXLS2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/752Y6NLBZDJLJ3XGVKZYEXLS2K/action/storage_attestation","attest_author":"https://pith.science/pith/752Y6NLBZDJLJ3XGVKZYEXLS2K/action/author_attestation","sign_citation":"https://pith.science/pith/752Y6NLBZDJLJ3XGVKZYEXLS2K/action/citation_signature","submit_replication":"https://pith.science/pith/752Y6NLBZDJLJ3XGVKZYEXLS2K/action/replication_record"}},"created_at":"2026-07-05T09:50:41.473638+00:00","updated_at":"2026-07-05T09:50:41.473638+00:00"}