{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RT7R7HU2DBJGZGDVR6NM4VCIYG","short_pith_number":"pith:RT7R7HU2","schema_version":"1.0","canonical_sha256":"8cff1f9e9a18526c98758f9ace5448c184b3473abc10f641348d642ca63ae547","source":{"kind":"arxiv","id":"1705.00053","version":1},"attestation_state":"computed","paper":{"title":"The Pose Knows: Video Forecasting by Generating Pose Futures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Jacob Walker, Kenneth Marino, Martial Hebert","submitted_at":"2017-04-28T19:46:47Z","abstract_excerpt":"Current approaches in video forecasting attempt to generate videos directly in pixel space using Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). However, since these approaches try to model all the structure and scene dynamics at once, in unconstrained settings they often generate uninterpretable results. Our insight is to model the forecasting problem at a higher level of abstraction. Specifically, we exploit human pose detectors as a free source of supervision and break the video forecasting problem into two discrete steps. First we explicitly model the high level "},"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":"1705.00053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-28T19:46:47Z","cross_cats_sorted":[],"title_canon_sha256":"7c6529642c1372eeafd687ce04dac89923a4d397ceb284c6b70f3bcc9c1e7274","abstract_canon_sha256":"84fc1bc11c2d135ad04e52f038a2a21ab800913106b04ec35cf407a29db66a5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:21.611825Z","signature_b64":"Nh89so1Y2+1iRae1RNbMWtqubGweV92C8CE4plf1HKVUyCgbGEuMxqiTAUqRVRVbj0Bd+eT45BYbxZ+ySBLtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cff1f9e9a18526c98758f9ace5448c184b3473abc10f641348d642ca63ae547","last_reissued_at":"2026-05-18T00:45:21.611231Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:21.611231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Pose Knows: Video Forecasting by Generating Pose Futures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Jacob Walker, Kenneth Marino, Martial Hebert","submitted_at":"2017-04-28T19:46:47Z","abstract_excerpt":"Current approaches in video forecasting attempt to generate videos directly in pixel space using Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). However, since these approaches try to model all the structure and scene dynamics at once, in unconstrained settings they often generate uninterpretable results. Our insight is to model the forecasting problem at a higher level of abstraction. Specifically, we exploit human pose detectors as a free source of supervision and break the video forecasting problem into two discrete steps. First we explicitly model the high level "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00053","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":""},"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":"1705.00053","created_at":"2026-05-18T00:45:21.611334+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.00053v1","created_at":"2026-05-18T00:45:21.611334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00053","created_at":"2026-05-18T00:45:21.611334+00:00"},{"alias_kind":"pith_short_12","alias_value":"RT7R7HU2DBJG","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"RT7R7HU2DBJGZGDV","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"RT7R7HU2","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RT7R7HU2DBJGZGDVR6NM4VCIYG","json":"https://pith.science/pith/RT7R7HU2DBJGZGDVR6NM4VCIYG.json","graph_json":"https://pith.science/api/pith-number/RT7R7HU2DBJGZGDVR6NM4VCIYG/graph.json","events_json":"https://pith.science/api/pith-number/RT7R7HU2DBJGZGDVR6NM4VCIYG/events.json","paper":"https://pith.science/paper/RT7R7HU2"},"agent_actions":{"view_html":"https://pith.science/pith/RT7R7HU2DBJGZGDVR6NM4VCIYG","download_json":"https://pith.science/pith/RT7R7HU2DBJGZGDVR6NM4VCIYG.json","view_paper":"https://pith.science/paper/RT7R7HU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.00053&json=true","fetch_graph":"https://pith.science/api/pith-number/RT7R7HU2DBJGZGDVR6NM4VCIYG/graph.json","fetch_events":"https://pith.science/api/pith-number/RT7R7HU2DBJGZGDVR6NM4VCIYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RT7R7HU2DBJGZGDVR6NM4VCIYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RT7R7HU2DBJGZGDVR6NM4VCIYG/action/storage_attestation","attest_author":"https://pith.science/pith/RT7R7HU2DBJGZGDVR6NM4VCIYG/action/author_attestation","sign_citation":"https://pith.science/pith/RT7R7HU2DBJGZGDVR6NM4VCIYG/action/citation_signature","submit_replication":"https://pith.science/pith/RT7R7HU2DBJGZGDVR6NM4VCIYG/action/replication_record"}},"created_at":"2026-05-18T00:45:21.611334+00:00","updated_at":"2026-05-18T00:45:21.611334+00:00"}