{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BWUYKR2GNKXTBCXYQ72T3AQXWN","short_pith_number":"pith:BWUYKR2G","schema_version":"1.0","canonical_sha256":"0da98547466aaf308af887f53d8217b359f1b8b76feef4d87fdbce062f67db5b","source":{"kind":"arxiv","id":"2203.07706","version":2},"attestation_state":"computed","paper":{"title":"ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chenjing Ding, Dongliang Wang, Jing Su, Liang Xu, Weihao Gan, Wei Wu, Wenjun Zeng, Xiaokang Yang, Xin Jin, Yichao Yan, Zhicheng Fang, Ziyang Song","submitted_at":"2022-03-15T07:50:12Z","abstract_excerpt":"We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions. Our approach consists of a powerful Action-conditioned motion TransFormer (ActFormer) under a GAN training scheme, equipped with a Gaussian Process latent prior. Such a design combines the strong spatio-temporal representation capacity of Transformer, superiority in generative modeling of GAN, and inherent temporal correlations from the latent prior. Furthermore, ActFormer can be naturally extended to multi-person moti"},"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":"2203.07706","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-15T07:50:12Z","cross_cats_sorted":["cs.GR","cs.MM"],"title_canon_sha256":"72ef7ed2308d5a575e7509fbc8aa6c45a7f2bf7f564035f038f862b28f32f042","abstract_canon_sha256":"2c2369ac849ca88176633e5e229d0913523c95e5749f3500417c7447e4873338"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:45.848207Z","signature_b64":"I4X6VCZ+2rBbwLeMucHqu9TLB+XgvQDkwBxFxdDofOeryylCL3rXSRlFIAvSa/2e2GCEJCsL41oGvAViJ78BCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0da98547466aaf308af887f53d8217b359f1b8b76feef4d87fdbce062f67db5b","last_reissued_at":"2026-07-05T05:18:45.847724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:45.847724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chenjing Ding, Dongliang Wang, Jing Su, Liang Xu, Weihao Gan, Wei Wu, Wenjun Zeng, Xiaokang Yang, Xin Jin, Yichao Yan, Zhicheng Fang, Ziyang Song","submitted_at":"2022-03-15T07:50:12Z","abstract_excerpt":"We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions. Our approach consists of a powerful Action-conditioned motion TransFormer (ActFormer) under a GAN training scheme, equipped with a Gaussian Process latent prior. Such a design combines the strong spatio-temporal representation capacity of Transformer, superiority in generative modeling of GAN, and inherent temporal correlations from the latent prior. Furthermore, ActFormer can be naturally extended to multi-person moti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07706","kind":"arxiv","version":2},"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/2203.07706/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":"2203.07706","created_at":"2026-07-05T05:18:45.847778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07706v2","created_at":"2026-07-05T05:18:45.847778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07706","created_at":"2026-07-05T05:18:45.847778+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWUYKR2GNKXT","created_at":"2026-07-05T05:18:45.847778+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWUYKR2GNKXTBCXY","created_at":"2026-07-05T05:18:45.847778+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWUYKR2G","created_at":"2026-07-05T05:18:45.847778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03191","citing_title":"Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward","ref_index":92,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWUYKR2GNKXTBCXYQ72T3AQXWN","json":"https://pith.science/pith/BWUYKR2GNKXTBCXYQ72T3AQXWN.json","graph_json":"https://pith.science/api/pith-number/BWUYKR2GNKXTBCXYQ72T3AQXWN/graph.json","events_json":"https://pith.science/api/pith-number/BWUYKR2GNKXTBCXYQ72T3AQXWN/events.json","paper":"https://pith.science/paper/BWUYKR2G"},"agent_actions":{"view_html":"https://pith.science/pith/BWUYKR2GNKXTBCXYQ72T3AQXWN","download_json":"https://pith.science/pith/BWUYKR2GNKXTBCXYQ72T3AQXWN.json","view_paper":"https://pith.science/paper/BWUYKR2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07706&json=true","fetch_graph":"https://pith.science/api/pith-number/BWUYKR2GNKXTBCXYQ72T3AQXWN/graph.json","fetch_events":"https://pith.science/api/pith-number/BWUYKR2GNKXTBCXYQ72T3AQXWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWUYKR2GNKXTBCXYQ72T3AQXWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWUYKR2GNKXTBCXYQ72T3AQXWN/action/storage_attestation","attest_author":"https://pith.science/pith/BWUYKR2GNKXTBCXYQ72T3AQXWN/action/author_attestation","sign_citation":"https://pith.science/pith/BWUYKR2GNKXTBCXYQ72T3AQXWN/action/citation_signature","submit_replication":"https://pith.science/pith/BWUYKR2GNKXTBCXYQ72T3AQXWN/action/replication_record"}},"created_at":"2026-07-05T05:18:45.847778+00:00","updated_at":"2026-07-05T05:18:45.847778+00:00"}