{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J33IQELAYMR724742OX4EZUENN","short_pith_number":"pith:J33IQELA","schema_version":"1.0","canonical_sha256":"4ef6881160c323fd73fcd3afc266846b64a5fe0a9549fc2257d35c3a6349b9f7","source":{"kind":"arxiv","id":"2404.10685","version":1},"attestation_state":"computed","paper":{"title":"Generating Human Interaction Motions in Scenes with Text Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Davis Rempe, Hongwei Yi, Justus Thies, Michael J. Black, Xue Bin Peng","submitted_at":"2024-04-16T16:04:38Z","abstract_excerpt":"We present TeSMo, a method for text-controlled scene-aware motion generation based on denoising diffusion models. Previous text-to-motion methods focus on characters in isolation without considering scenes due to the limited availability of datasets that include motion, text descriptions, and interactive scenes. Our approach begins with pre-training a scene-agnostic text-to-motion diffusion model, emphasizing goal-reaching constraints on large-scale motion-capture datasets. We then enhance this model with a scene-aware component, fine-tuned using data augmented with detailed scene information,"},"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":"2404.10685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T16:04:38Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"71babaf45bc4e9cf6d61757ebff6d8937b4af3e157c79962f92b4442012f5284","abstract_canon_sha256":"3368be21835959d7374d715e3a96254ce7130e2283552f3ad9b46f5e87319d22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:43.654937Z","signature_b64":"RdwMcrc4ElMPDI/y5u2tYEovUPQocldRjFLggUI0f9sqIe4haZLDnPn2aTogHhK/Btjc3wXlx2c3MevQyUUCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ef6881160c323fd73fcd3afc266846b64a5fe0a9549fc2257d35c3a6349b9f7","last_reissued_at":"2026-07-05T08:08:43.654372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:43.654372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Human Interaction Motions in Scenes with Text Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Davis Rempe, Hongwei Yi, Justus Thies, Michael J. Black, Xue Bin Peng","submitted_at":"2024-04-16T16:04:38Z","abstract_excerpt":"We present TeSMo, a method for text-controlled scene-aware motion generation based on denoising diffusion models. Previous text-to-motion methods focus on characters in isolation without considering scenes due to the limited availability of datasets that include motion, text descriptions, and interactive scenes. Our approach begins with pre-training a scene-agnostic text-to-motion diffusion model, emphasizing goal-reaching constraints on large-scale motion-capture datasets. We then enhance this model with a scene-aware component, fine-tuned using data augmented with detailed scene information,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10685","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/2404.10685/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":"2404.10685","created_at":"2026-07-05T08:08:43.654436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10685v1","created_at":"2026-07-05T08:08:43.654436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10685","created_at":"2026-07-05T08:08:43.654436+00:00"},{"alias_kind":"pith_short_12","alias_value":"J33IQELAYMR7","created_at":"2026-07-05T08:08:43.654436+00:00"},{"alias_kind":"pith_short_16","alias_value":"J33IQELAYMR72474","created_at":"2026-07-05T08:08:43.654436+00:00"},{"alias_kind":"pith_short_8","alias_value":"J33IQELA","created_at":"2026-07-05T08:08:43.654436+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07880","citing_title":"GIRAF: Towards Generalizable Human Interactions with Articulated Objects","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04843","citing_title":"InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J33IQELAYMR724742OX4EZUENN","json":"https://pith.science/pith/J33IQELAYMR724742OX4EZUENN.json","graph_json":"https://pith.science/api/pith-number/J33IQELAYMR724742OX4EZUENN/graph.json","events_json":"https://pith.science/api/pith-number/J33IQELAYMR724742OX4EZUENN/events.json","paper":"https://pith.science/paper/J33IQELA"},"agent_actions":{"view_html":"https://pith.science/pith/J33IQELAYMR724742OX4EZUENN","download_json":"https://pith.science/pith/J33IQELAYMR724742OX4EZUENN.json","view_paper":"https://pith.science/paper/J33IQELA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10685&json=true","fetch_graph":"https://pith.science/api/pith-number/J33IQELAYMR724742OX4EZUENN/graph.json","fetch_events":"https://pith.science/api/pith-number/J33IQELAYMR724742OX4EZUENN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J33IQELAYMR724742OX4EZUENN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J33IQELAYMR724742OX4EZUENN/action/storage_attestation","attest_author":"https://pith.science/pith/J33IQELAYMR724742OX4EZUENN/action/author_attestation","sign_citation":"https://pith.science/pith/J33IQELAYMR724742OX4EZUENN/action/citation_signature","submit_replication":"https://pith.science/pith/J33IQELAYMR724742OX4EZUENN/action/replication_record"}},"created_at":"2026-07-05T08:08:43.654436+00:00","updated_at":"2026-07-05T08:08:43.654436+00:00"}