{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZYJ5R4QMTQJKIVAJCQ2UI2JLQR","short_pith_number":"pith:ZYJ5R4QM","schema_version":"1.0","canonical_sha256":"ce13d8f20c9c12a45409143544692b84427c1b4083daa7cc53ec35d114435716","source":{"kind":"arxiv","id":"2407.11494","version":1},"attestation_state":"computed","paper":{"title":"Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guowei Xu, Jiale Tao, Lixin Duan, Wen Li","submitted_at":"2024-07-16T08:31:59Z","abstract_excerpt":"In the realm of stochastic human motion prediction (SHMP), researchers have often turned to generative models like GANS, VAEs and diffusion models. However, most previous approaches have struggled to accurately predict motions that are both realistic and coherent with past motion due to a lack of guidance on the latent distribution. In this paper, we introduce Semantic Latent Directions (SLD) as a solution to this challenge, aiming to constrain the latent space to learn meaningful motion semantics and enhance the accuracy of SHMP. SLD defines a series of orthogonal latent directions and repres"},"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":"2407.11494","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T08:31:59Z","cross_cats_sorted":[],"title_canon_sha256":"845e97d16c537f628220124e50d659218ce9173c23a46a658ddb76fa9b4622dd","abstract_canon_sha256":"1a5299bb6df17c0e794dcecf3c399b95ec2f2caf2e7877b0e4538d0dbc1406ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:25.307434Z","signature_b64":"BKAsGx8SmjQD123K1qy1I2WxPg2Quiae2dMEAJqGCqmLPFmvzhSzKZSEAGywyJ03Oa8hXX+7ZtJCwI7c/R0gCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce13d8f20c9c12a45409143544692b84427c1b4083daa7cc53ec35d114435716","last_reissued_at":"2026-07-05T08:44:25.306989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:25.306989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guowei Xu, Jiale Tao, Lixin Duan, Wen Li","submitted_at":"2024-07-16T08:31:59Z","abstract_excerpt":"In the realm of stochastic human motion prediction (SHMP), researchers have often turned to generative models like GANS, VAEs and diffusion models. However, most previous approaches have struggled to accurately predict motions that are both realistic and coherent with past motion due to a lack of guidance on the latent distribution. In this paper, we introduce Semantic Latent Directions (SLD) as a solution to this challenge, aiming to constrain the latent space to learn meaningful motion semantics and enhance the accuracy of SHMP. SLD defines a series of orthogonal latent directions and repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11494","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/2407.11494/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":"2407.11494","created_at":"2026-07-05T08:44:25.307052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11494v1","created_at":"2026-07-05T08:44:25.307052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11494","created_at":"2026-07-05T08:44:25.307052+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYJ5R4QMTQJK","created_at":"2026-07-05T08:44:25.307052+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYJ5R4QMTQJKIVAJ","created_at":"2026-07-05T08:44:25.307052+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYJ5R4QM","created_at":"2026-07-05T08:44:25.307052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18883","citing_title":"MotionMap: Representing Multimodality in Human Pose Forecasting","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR","json":"https://pith.science/pith/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR.json","graph_json":"https://pith.science/api/pith-number/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR/graph.json","events_json":"https://pith.science/api/pith-number/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR/events.json","paper":"https://pith.science/paper/ZYJ5R4QM"},"agent_actions":{"view_html":"https://pith.science/pith/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR","download_json":"https://pith.science/pith/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR.json","view_paper":"https://pith.science/paper/ZYJ5R4QM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11494&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR/action/storage_attestation","attest_author":"https://pith.science/pith/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR/action/author_attestation","sign_citation":"https://pith.science/pith/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR/action/citation_signature","submit_replication":"https://pith.science/pith/ZYJ5R4QMTQJKIVAJCQ2UI2JLQR/action/replication_record"}},"created_at":"2026-07-05T08:44:25.307052+00:00","updated_at":"2026-07-05T08:44:25.307052+00:00"}