{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QHUP7TAQKUGG65MM7LFEZ6Q2R7","short_pith_number":"pith:QHUP7TAQ","schema_version":"1.0","canonical_sha256":"81e8ffcc10550c6f758cfaca4cfa1a8fd912875b259a55165d553f2c346c1d16","source":{"kind":"arxiv","id":"2105.08715","version":2},"attestation_state":"computed","paper":{"title":"Human Motion Prediction Using Manifold-Aware Wasserstein GAN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Angela Bartolo, Baptiste Chopin, Mohamed Daoudi, Naima Otberdout","submitted_at":"2021-05-18T17:56:10Z","abstract_excerpt":"Human motion prediction aims to forecast future human poses given a prior pose sequence. The discontinuity of the predicted motion and the performance deterioration in long-term horizons are still the main challenges encountered in current literature. In this work, we tackle these issues by using a compact manifold-valued representation of human motion. Specifically, we model the temporal evolution of the 3D human poses as trajectory, what allows us to map human motions to single points on a sphere manifold. To learn these non-Euclidean representations, we build a manifold-aware Wasserstein ge"},"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":"2105.08715","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-18T17:56:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14ccb2b01c21c319b4971d13ea8946edac88b7dadfc7127a19ec68790e16d49f","abstract_canon_sha256":"75da8cb09d45a86fdebd200eba8792385e7677105b1488cb9a2aeba230a33ccb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:42.187685Z","signature_b64":"L7Q/JphF4wr/BnVPgVUINbT4UVHpJo1Fcl9EHUfbJpUcXmBNG4hDPQvHkAGVUk3dY354JFd/KtCBSaJS50qXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81e8ffcc10550c6f758cfaca4cfa1a8fd912875b259a55165d553f2c346c1d16","last_reissued_at":"2026-07-05T02:58:42.187164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:42.187164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human Motion Prediction Using Manifold-Aware Wasserstein GAN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Angela Bartolo, Baptiste Chopin, Mohamed Daoudi, Naima Otberdout","submitted_at":"2021-05-18T17:56:10Z","abstract_excerpt":"Human motion prediction aims to forecast future human poses given a prior pose sequence. The discontinuity of the predicted motion and the performance deterioration in long-term horizons are still the main challenges encountered in current literature. In this work, we tackle these issues by using a compact manifold-valued representation of human motion. Specifically, we model the temporal evolution of the 3D human poses as trajectory, what allows us to map human motions to single points on a sphere manifold. To learn these non-Euclidean representations, we build a manifold-aware Wasserstein ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08715","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/2105.08715/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":"2105.08715","created_at":"2026-07-05T02:58:42.187221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.08715v2","created_at":"2026-07-05T02:58:42.187221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08715","created_at":"2026-07-05T02:58:42.187221+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHUP7TAQKUGG","created_at":"2026-07-05T02:58:42.187221+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHUP7TAQKUGG65MM","created_at":"2026-07-05T02:58:42.187221+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHUP7TAQ","created_at":"2026-07-05T02:58:42.187221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10458","citing_title":"Motion Generation Review: Exploring Deep Learning for Lifelike Animation with Manifold","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QHUP7TAQKUGG65MM7LFEZ6Q2R7","json":"https://pith.science/pith/QHUP7TAQKUGG65MM7LFEZ6Q2R7.json","graph_json":"https://pith.science/api/pith-number/QHUP7TAQKUGG65MM7LFEZ6Q2R7/graph.json","events_json":"https://pith.science/api/pith-number/QHUP7TAQKUGG65MM7LFEZ6Q2R7/events.json","paper":"https://pith.science/paper/QHUP7TAQ"},"agent_actions":{"view_html":"https://pith.science/pith/QHUP7TAQKUGG65MM7LFEZ6Q2R7","download_json":"https://pith.science/pith/QHUP7TAQKUGG65MM7LFEZ6Q2R7.json","view_paper":"https://pith.science/paper/QHUP7TAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.08715&json=true","fetch_graph":"https://pith.science/api/pith-number/QHUP7TAQKUGG65MM7LFEZ6Q2R7/graph.json","fetch_events":"https://pith.science/api/pith-number/QHUP7TAQKUGG65MM7LFEZ6Q2R7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHUP7TAQKUGG65MM7LFEZ6Q2R7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHUP7TAQKUGG65MM7LFEZ6Q2R7/action/storage_attestation","attest_author":"https://pith.science/pith/QHUP7TAQKUGG65MM7LFEZ6Q2R7/action/author_attestation","sign_citation":"https://pith.science/pith/QHUP7TAQKUGG65MM7LFEZ6Q2R7/action/citation_signature","submit_replication":"https://pith.science/pith/QHUP7TAQKUGG65MM7LFEZ6Q2R7/action/replication_record"}},"created_at":"2026-07-05T02:58:42.187221+00:00","updated_at":"2026-07-05T02:58:42.187221+00:00"}