{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z72WD2SHRZU5TSZDGTR5WDL2YD","short_pith_number":"pith:Z72WD2SH","schema_version":"1.0","canonical_sha256":"cff561ea478e69d9cb2334e3db0d7ac0c7b2d445eab6c3845181f31c31a67e87","source":{"kind":"arxiv","id":"2104.02300","version":1},"attestation_state":"computed","paper":{"title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xiao, Jingdong Wang, Ke Sun, Zhaoxiang Zhang, Zigang Geng","submitted_at":"2021-04-06T05:54:46Z","abstract_excerpt":"In this paper, we are interested in the bottom-up paradigm of estimating human poses from an image. We study the dense keypoint regression framework that is previously inferior to the keypoint detection and grouping framework. Our motivation is that regressing keypoint positions accurately needs to learn representations that focus on the keypoint regions.\n  We present a simple yet effective approach, named disentangled keypoint regression (DEKR). We adopt adaptive convolutions through pixel-wise spatial transformer to activate the pixels in the keypoint regions and accordingly learn representa"},"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":"2104.02300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-06T05:54:46Z","cross_cats_sorted":[],"title_canon_sha256":"e0f7d22a780e4ed16b7a7090089884b6bd67d2d80d803cd3e65d95a1cd91ce4f","abstract_canon_sha256":"3512f096f45249d96cf7368298bbcc569a9926ef68aec8e36c28edf4191699bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:16.827856Z","signature_b64":"wmgn35G7QasAyOPBgHdGLLvc1ubW9g4Dv5TV7sPdr2H7pO2oNhQJ2tH2LAzw0zBF1/B8GG+6jLEiA6grp5XTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cff561ea478e69d9cb2334e3db0d7ac0c7b2d445eab6c3845181f31c31a67e87","last_reissued_at":"2026-07-05T02:29:16.827429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:16.827429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xiao, Jingdong Wang, Ke Sun, Zhaoxiang Zhang, Zigang Geng","submitted_at":"2021-04-06T05:54:46Z","abstract_excerpt":"In this paper, we are interested in the bottom-up paradigm of estimating human poses from an image. We study the dense keypoint regression framework that is previously inferior to the keypoint detection and grouping framework. Our motivation is that regressing keypoint positions accurately needs to learn representations that focus on the keypoint regions.\n  We present a simple yet effective approach, named disentangled keypoint regression (DEKR). We adopt adaptive convolutions through pixel-wise spatial transformer to activate the pixels in the keypoint regions and accordingly learn representa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02300","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/2104.02300/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":"2104.02300","created_at":"2026-07-05T02:29:16.827495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02300v1","created_at":"2026-07-05T02:29:16.827495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02300","created_at":"2026-07-05T02:29:16.827495+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z72WD2SHRZU5","created_at":"2026-07-05T02:29:16.827495+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z72WD2SHRZU5TSZD","created_at":"2026-07-05T02:29:16.827495+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z72WD2SH","created_at":"2026-07-05T02:29:16.827495+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02773","citing_title":"Unsupervised Domain Adaptation for Occlusion Resilient Human Pose Estimation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z72WD2SHRZU5TSZDGTR5WDL2YD","json":"https://pith.science/pith/Z72WD2SHRZU5TSZDGTR5WDL2YD.json","graph_json":"https://pith.science/api/pith-number/Z72WD2SHRZU5TSZDGTR5WDL2YD/graph.json","events_json":"https://pith.science/api/pith-number/Z72WD2SHRZU5TSZDGTR5WDL2YD/events.json","paper":"https://pith.science/paper/Z72WD2SH"},"agent_actions":{"view_html":"https://pith.science/pith/Z72WD2SHRZU5TSZDGTR5WDL2YD","download_json":"https://pith.science/pith/Z72WD2SHRZU5TSZDGTR5WDL2YD.json","view_paper":"https://pith.science/paper/Z72WD2SH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02300&json=true","fetch_graph":"https://pith.science/api/pith-number/Z72WD2SHRZU5TSZDGTR5WDL2YD/graph.json","fetch_events":"https://pith.science/api/pith-number/Z72WD2SHRZU5TSZDGTR5WDL2YD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z72WD2SHRZU5TSZDGTR5WDL2YD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z72WD2SHRZU5TSZDGTR5WDL2YD/action/storage_attestation","attest_author":"https://pith.science/pith/Z72WD2SHRZU5TSZDGTR5WDL2YD/action/author_attestation","sign_citation":"https://pith.science/pith/Z72WD2SHRZU5TSZDGTR5WDL2YD/action/citation_signature","submit_replication":"https://pith.science/pith/Z72WD2SHRZU5TSZDGTR5WDL2YD/action/replication_record"}},"created_at":"2026-07-05T02:29:16.827495+00:00","updated_at":"2026-07-05T02:29:16.827495+00:00"}