{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:73GBAGXKF3JYKEHAF3EAKM2F2Y","short_pith_number":"pith:73GBAGXK","schema_version":"1.0","canonical_sha256":"fecc101aea2ed38510e02ec8053345d6284e948ddbde4fb57bd4012c340a6e50","source":{"kind":"arxiv","id":"2003.04894","version":3},"attestation_state":"computed","paper":{"title":"HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangbo Lu, Kui Jia, Kun Zhou, Nianjuan Jiang, Xiaoguang Han","submitted_at":"2020-03-10T04:03:45Z","abstract_excerpt":"Estimating 3D human pose from a single image is a challenging task. This work attempts to address the uncertainty of lifting the detected 2D joints to the 3D space by introducing an intermediate state-Part-Centric Heatmap Triplets (HEMlets), which shortens the gap between the 2D observation and the 3D interpretation. The HEMlets utilize three joint-heatmaps to represent the relative depth information of the end-joints for each skeletal body part. In our approach, a Convolutional Network (ConvNet) is first trained to predict HEMlets from the input image, followed by a volumetric joint-heatmap r"},"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":"2003.04894","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-10T04:03:45Z","cross_cats_sorted":[],"title_canon_sha256":"280bb314f4dd9b7e3acbb8041353d3e16a1018db801fa9d11ad189996fd23015","abstract_canon_sha256":"a7a271b0a4c50ba24f389442cb3c4eb79d28acecfafebd793820bb9889c40cae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:07.378780Z","signature_b64":"17dksv5vFjXEpKGSKEQm6CLNx6TsmyWLx9JAimdENUmNv8mXdXIJNE0Ae5dECg/9Ds/o691KzuNoNwxn159sCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fecc101aea2ed38510e02ec8053345d6284e948ddbde4fb57bd4012c340a6e50","last_reissued_at":"2026-07-05T02:06:07.378368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:07.378368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangbo Lu, Kui Jia, Kun Zhou, Nianjuan Jiang, Xiaoguang Han","submitted_at":"2020-03-10T04:03:45Z","abstract_excerpt":"Estimating 3D human pose from a single image is a challenging task. This work attempts to address the uncertainty of lifting the detected 2D joints to the 3D space by introducing an intermediate state-Part-Centric Heatmap Triplets (HEMlets), which shortens the gap between the 2D observation and the 3D interpretation. The HEMlets utilize three joint-heatmaps to represent the relative depth information of the end-joints for each skeletal body part. In our approach, a Convolutional Network (ConvNet) is first trained to predict HEMlets from the input image, followed by a volumetric joint-heatmap r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04894","kind":"arxiv","version":3},"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/2003.04894/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":"2003.04894","created_at":"2026-07-05T02:06:07.378426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.04894v3","created_at":"2026-07-05T02:06:07.378426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04894","created_at":"2026-07-05T02:06:07.378426+00:00"},{"alias_kind":"pith_short_12","alias_value":"73GBAGXKF3JY","created_at":"2026-07-05T02:06:07.378426+00:00"},{"alias_kind":"pith_short_16","alias_value":"73GBAGXKF3JYKEHA","created_at":"2026-07-05T02:06:07.378426+00:00"},{"alias_kind":"pith_short_8","alias_value":"73GBAGXK","created_at":"2026-07-05T02:06:07.378426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20763","citing_title":"KASportsFormer: Kinematic Anatomy Enhanced Transformer for 3D Human Pose Estimation on Short Sports Scene Video","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73GBAGXKF3JYKEHAF3EAKM2F2Y","json":"https://pith.science/pith/73GBAGXKF3JYKEHAF3EAKM2F2Y.json","graph_json":"https://pith.science/api/pith-number/73GBAGXKF3JYKEHAF3EAKM2F2Y/graph.json","events_json":"https://pith.science/api/pith-number/73GBAGXKF3JYKEHAF3EAKM2F2Y/events.json","paper":"https://pith.science/paper/73GBAGXK"},"agent_actions":{"view_html":"https://pith.science/pith/73GBAGXKF3JYKEHAF3EAKM2F2Y","download_json":"https://pith.science/pith/73GBAGXKF3JYKEHAF3EAKM2F2Y.json","view_paper":"https://pith.science/paper/73GBAGXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.04894&json=true","fetch_graph":"https://pith.science/api/pith-number/73GBAGXKF3JYKEHAF3EAKM2F2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/73GBAGXKF3JYKEHAF3EAKM2F2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73GBAGXKF3JYKEHAF3EAKM2F2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73GBAGXKF3JYKEHAF3EAKM2F2Y/action/storage_attestation","attest_author":"https://pith.science/pith/73GBAGXKF3JYKEHAF3EAKM2F2Y/action/author_attestation","sign_citation":"https://pith.science/pith/73GBAGXKF3JYKEHAF3EAKM2F2Y/action/citation_signature","submit_replication":"https://pith.science/pith/73GBAGXKF3JYKEHAF3EAKM2F2Y/action/replication_record"}},"created_at":"2026-07-05T02:06:07.378426+00:00","updated_at":"2026-07-05T02:06:07.378426+00:00"}