{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7IGMSFRM3VEFXLQLHFNWFDVO3G","short_pith_number":"pith:7IGMSFRM","schema_version":"1.0","canonical_sha256":"fa0cc9162cdd485bae0b395b628eaed9821b6a39b6bdf4260e0eceef508b0128","source":{"kind":"arxiv","id":"2410.10010","version":3},"attestation_state":"computed","paper":{"title":"InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuan Guo, Li Cheng, Muhammad Gohar Javed, Xingyu Li","submitted_at":"2024-10-13T21:11:04Z","abstract_excerpt":"Generating realistic 3D human-human interactions from textual descriptions remains a challenging task. Existing approaches, typically based on diffusion models, often produce results lacking realism and fidelity. In this work, we introduce InterMask, a novel framework for generating human interactions using collaborative masked modeling in discrete space. InterMask first employs a VQ-VAE to transform each motion sequence into a 2D discrete motion token map. Unlike traditional 1D VQ token maps, it better preserves fine-grained spatio-temporal details and promotes spatial awareness within each t"},"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":"2410.10010","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-13T21:11:04Z","cross_cats_sorted":[],"title_canon_sha256":"827791dfcb7221be261e7dab6dd71709d62e874e59be39f46eb41008bccada7d","abstract_canon_sha256":"595cf5116000433474298ed544107df22768bceb5c34debdc1d5f4c10c0a2f95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:07.517275Z","signature_b64":"V8gv6lvv0GM96813CegSDFHraf8VjcK59Kp/FMYonb3I+iBEU3TaZfDP3u6ttm7iywrWfLu1UqtvUKDpz7kXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa0cc9162cdd485bae0b395b628eaed9821b6a39b6bdf4260e0eceef508b0128","last_reissued_at":"2026-07-05T10:22:07.516693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:07.516693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuan Guo, Li Cheng, Muhammad Gohar Javed, Xingyu Li","submitted_at":"2024-10-13T21:11:04Z","abstract_excerpt":"Generating realistic 3D human-human interactions from textual descriptions remains a challenging task. Existing approaches, typically based on diffusion models, often produce results lacking realism and fidelity. In this work, we introduce InterMask, a novel framework for generating human interactions using collaborative masked modeling in discrete space. InterMask first employs a VQ-VAE to transform each motion sequence into a 2D discrete motion token map. Unlike traditional 1D VQ token maps, it better preserves fine-grained spatio-temporal details and promotes spatial awareness within each t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10010","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/2410.10010/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":"2410.10010","created_at":"2026-07-05T10:22:07.516758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10010v3","created_at":"2026-07-05T10:22:07.516758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10010","created_at":"2026-07-05T10:22:07.516758+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IGMSFRM3VEF","created_at":"2026-07-05T10:22:07.516758+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IGMSFRM3VEFXLQL","created_at":"2026-07-05T10:22:07.516758+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IGMSFRM","created_at":"2026-07-05T10:22:07.516758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02973","citing_title":"Exploring Motion-Language Alignment for Text-driven Motion Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00517","citing_title":"PhysiGen: Integrating Collision-Aware Physical Constraints for High-Fidelity Human-Human Interaction Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20336","citing_title":"Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IGMSFRM3VEFXLQLHFNWFDVO3G","json":"https://pith.science/pith/7IGMSFRM3VEFXLQLHFNWFDVO3G.json","graph_json":"https://pith.science/api/pith-number/7IGMSFRM3VEFXLQLHFNWFDVO3G/graph.json","events_json":"https://pith.science/api/pith-number/7IGMSFRM3VEFXLQLHFNWFDVO3G/events.json","paper":"https://pith.science/paper/7IGMSFRM"},"agent_actions":{"view_html":"https://pith.science/pith/7IGMSFRM3VEFXLQLHFNWFDVO3G","download_json":"https://pith.science/pith/7IGMSFRM3VEFXLQLHFNWFDVO3G.json","view_paper":"https://pith.science/paper/7IGMSFRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10010&json=true","fetch_graph":"https://pith.science/api/pith-number/7IGMSFRM3VEFXLQLHFNWFDVO3G/graph.json","fetch_events":"https://pith.science/api/pith-number/7IGMSFRM3VEFXLQLHFNWFDVO3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IGMSFRM3VEFXLQLHFNWFDVO3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IGMSFRM3VEFXLQLHFNWFDVO3G/action/storage_attestation","attest_author":"https://pith.science/pith/7IGMSFRM3VEFXLQLHFNWFDVO3G/action/author_attestation","sign_citation":"https://pith.science/pith/7IGMSFRM3VEFXLQLHFNWFDVO3G/action/citation_signature","submit_replication":"https://pith.science/pith/7IGMSFRM3VEFXLQLHFNWFDVO3G/action/replication_record"}},"created_at":"2026-07-05T10:22:07.516758+00:00","updated_at":"2026-07-05T10:22:07.516758+00:00"}