{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JHNJJVTSM2IBRM4RGMGFJXMSW6","short_pith_number":"pith:JHNJJVTS","schema_version":"1.0","canonical_sha256":"49da94d672669018b391330c54dd92b79c73e5d857dd55ebf262d1d8d805902a","source":{"kind":"arxiv","id":"1704.02827","version":2},"attestation_state":"computed","paper":{"title":"Learning Human Motion Models for Long-term Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Emre Aksan, Jie Song, Otmar Hilliges, Partha Ghosh","submitted_at":"2017-04-10T12:22:22Z","abstract_excerpt":"We propose a new architecture for the learning of predictive spatio-temporal motion models from data alone. Our approach, dubbed the Dropout Autoencoder LSTM, is capable of synthesizing natural looking motion sequences over long time horizons without catastrophic drift or motion degradation. The model consists of two components, a 3-layer recurrent neural network to model temporal aspects and a novel auto-encoder that is trained to implicitly recover the spatial structure of the human skeleton via randomly removing information about joints during training time. This Dropout Autoencoder (D-AE) "},"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":"1704.02827","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-10T12:22:22Z","cross_cats_sorted":[],"title_canon_sha256":"b1f6b8f46044c449f5fc75e8ea7b6eef38b904e120ba936dc57d2148e1793063","abstract_canon_sha256":"be3bf5d5c635a069dbd605773597cd4d986f6bb744917c97cee25c71a777fda7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:01.549770Z","signature_b64":"jC4k7HCiY83ixImYkeFEiuiQ9NsZI/VkW/4/cJ9AR9FDn/+j1vmHlUki9cE965+gjw2LyJV/0PNRkjNgHSkPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49da94d672669018b391330c54dd92b79c73e5d857dd55ebf262d1d8d805902a","last_reissued_at":"2026-05-18T00:29:01.549345Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:01.549345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Human Motion Models for Long-term Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Emre Aksan, Jie Song, Otmar Hilliges, Partha Ghosh","submitted_at":"2017-04-10T12:22:22Z","abstract_excerpt":"We propose a new architecture for the learning of predictive spatio-temporal motion models from data alone. Our approach, dubbed the Dropout Autoencoder LSTM, is capable of synthesizing natural looking motion sequences over long time horizons without catastrophic drift or motion degradation. The model consists of two components, a 3-layer recurrent neural network to model temporal aspects and a novel auto-encoder that is trained to implicitly recover the spatial structure of the human skeleton via randomly removing information about joints during training time. This Dropout Autoencoder (D-AE) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02827","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":""},"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":"1704.02827","created_at":"2026-05-18T00:29:01.549411+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.02827v2","created_at":"2026-05-18T00:29:01.549411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02827","created_at":"2026-05-18T00:29:01.549411+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHNJJVTSM2IB","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHNJJVTSM2IBRM4R","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHNJJVTS","created_at":"2026-05-18T12:31:24.725408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.10585","citing_title":"A neural network based post-filter for speech-driven head motion synthesis","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JHNJJVTSM2IBRM4RGMGFJXMSW6","json":"https://pith.science/pith/JHNJJVTSM2IBRM4RGMGFJXMSW6.json","graph_json":"https://pith.science/api/pith-number/JHNJJVTSM2IBRM4RGMGFJXMSW6/graph.json","events_json":"https://pith.science/api/pith-number/JHNJJVTSM2IBRM4RGMGFJXMSW6/events.json","paper":"https://pith.science/paper/JHNJJVTS"},"agent_actions":{"view_html":"https://pith.science/pith/JHNJJVTSM2IBRM4RGMGFJXMSW6","download_json":"https://pith.science/pith/JHNJJVTSM2IBRM4RGMGFJXMSW6.json","view_paper":"https://pith.science/paper/JHNJJVTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.02827&json=true","fetch_graph":"https://pith.science/api/pith-number/JHNJJVTSM2IBRM4RGMGFJXMSW6/graph.json","fetch_events":"https://pith.science/api/pith-number/JHNJJVTSM2IBRM4RGMGFJXMSW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHNJJVTSM2IBRM4RGMGFJXMSW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHNJJVTSM2IBRM4RGMGFJXMSW6/action/storage_attestation","attest_author":"https://pith.science/pith/JHNJJVTSM2IBRM4RGMGFJXMSW6/action/author_attestation","sign_citation":"https://pith.science/pith/JHNJJVTSM2IBRM4RGMGFJXMSW6/action/citation_signature","submit_replication":"https://pith.science/pith/JHNJJVTSM2IBRM4RGMGFJXMSW6/action/replication_record"}},"created_at":"2026-05-18T00:29:01.549411+00:00","updated_at":"2026-05-18T00:29:01.549411+00:00"}