{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L7JA2TCTIUV672M4TLBG4V6N7X","short_pith_number":"pith:L7JA2TCT","schema_version":"1.0","canonical_sha256":"5fd20d4c53452befe99c9ac26e57cdfde4e9a980533e4f9980c298128b487c66","source":{"kind":"arxiv","id":"2310.12978","version":1},"attestation_state":"computed","paper":{"title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Heung-Yeung Shum, Jing Lin, Lei Zhang, Ling-Hao Chen, Ruimao Zhang, Shunlin Lu","submitted_at":"2023-10-19T17:59:46Z","abstract_excerpt":"This work targets a novel text-driven whole-body motion generation task, which takes a given textual description as input and aims at generating high-quality, diverse, and coherent facial expressions, hand gestures, and body motions simultaneously. Previous works on text-driven motion generation tasks mainly have two limitations: they ignore the key role of fine-grained hand and face controlling in vivid whole-body motion generation, and lack a good alignment between text and motion. To address such limitations, we propose a Text-aligned whOle-body Motion generATiOn framework, named HumanTOMAT"},"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":"2310.12978","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-19T17:59:46Z","cross_cats_sorted":[],"title_canon_sha256":"884621b0617b27146eed9d5dd00c75479800df61cdd3a60d61cc324df6d958ed","abstract_canon_sha256":"5fddb009075d495524e483dcafcc884980dd1a066d551b8cffc38c6ce48bc666"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:45.203829Z","signature_b64":"21l9zW3QnEb9otrFMTGa7KQGMzC3ym1SQfssD271j7Gwr4/ktAwPCNHHT1p+xNngYwvGIZVuQI5JfgrMmfQQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fd20d4c53452befe99c9ac26e57cdfde4e9a980533e4f9980c298128b487c66","last_reissued_at":"2026-07-05T07:02:45.203350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:45.203350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Heung-Yeung Shum, Jing Lin, Lei Zhang, Ling-Hao Chen, Ruimao Zhang, Shunlin Lu","submitted_at":"2023-10-19T17:59:46Z","abstract_excerpt":"This work targets a novel text-driven whole-body motion generation task, which takes a given textual description as input and aims at generating high-quality, diverse, and coherent facial expressions, hand gestures, and body motions simultaneously. Previous works on text-driven motion generation tasks mainly have two limitations: they ignore the key role of fine-grained hand and face controlling in vivid whole-body motion generation, and lack a good alignment between text and motion. To address such limitations, we propose a Text-aligned whOle-body Motion generATiOn framework, named HumanTOMAT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12978","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/2310.12978/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":"2310.12978","created_at":"2026-07-05T07:02:45.203415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12978v1","created_at":"2026-07-05T07:02:45.203415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12978","created_at":"2026-07-05T07:02:45.203415+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7JA2TCTIUV6","created_at":"2026-07-05T07:02:45.203415+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7JA2TCTIUV672M4","created_at":"2026-07-05T07:02:45.203415+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7JA2TCT","created_at":"2026-07-05T07:02:45.203415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07880","citing_title":"GIRAF: Towards Generalizable Human Interactions with Articulated Objects","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27508","citing_title":"SASI: Leveraging Sub-Action Semantics for Robust Early Action Recognition in Human-Robot Interaction","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19105","citing_title":"EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7JA2TCTIUV672M4TLBG4V6N7X","json":"https://pith.science/pith/L7JA2TCTIUV672M4TLBG4V6N7X.json","graph_json":"https://pith.science/api/pith-number/L7JA2TCTIUV672M4TLBG4V6N7X/graph.json","events_json":"https://pith.science/api/pith-number/L7JA2TCTIUV672M4TLBG4V6N7X/events.json","paper":"https://pith.science/paper/L7JA2TCT"},"agent_actions":{"view_html":"https://pith.science/pith/L7JA2TCTIUV672M4TLBG4V6N7X","download_json":"https://pith.science/pith/L7JA2TCTIUV672M4TLBG4V6N7X.json","view_paper":"https://pith.science/paper/L7JA2TCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12978&json=true","fetch_graph":"https://pith.science/api/pith-number/L7JA2TCTIUV672M4TLBG4V6N7X/graph.json","fetch_events":"https://pith.science/api/pith-number/L7JA2TCTIUV672M4TLBG4V6N7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7JA2TCTIUV672M4TLBG4V6N7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7JA2TCTIUV672M4TLBG4V6N7X/action/storage_attestation","attest_author":"https://pith.science/pith/L7JA2TCTIUV672M4TLBG4V6N7X/action/author_attestation","sign_citation":"https://pith.science/pith/L7JA2TCTIUV672M4TLBG4V6N7X/action/citation_signature","submit_replication":"https://pith.science/pith/L7JA2TCTIUV672M4TLBG4V6N7X/action/replication_record"}},"created_at":"2026-07-05T07:02:45.203415+00:00","updated_at":"2026-07-05T07:02:45.203415+00:00"}