{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7DU5UD7WSHBMVB7CLR2I7PLXUG","short_pith_number":"pith:7DU5UD7W","schema_version":"1.0","canonical_sha256":"f8e9da0ff691c2ca87e25c748fbd77a195870162c68c1561a29ddfec238bd10f","source":{"kind":"arxiv","id":"2103.10180","version":1},"attestation_state":"computed","paper":{"title":"OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Andreas Savakis, Bruno Artacho","submitted_at":"2021-03-18T11:30:31Z","abstract_excerpt":"We propose OmniPose, a single-pass, end-to-end trainable framework, that achieves state-of-the-art results for multi-person pose estimation. Using a novel waterfall module, the OmniPose architecture leverages multi-scale feature representations that increase the effectiveness of backbone feature extractors, without the need for post-processing. OmniPose incorporates contextual information across scales and joint localization with Gaussian heatmap modulation at the multi-scale feature extractor to estimate human pose with state-of-the-art accuracy. The multi-scale representations, obtained by t"},"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":"2103.10180","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-18T11:30:31Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"e817abdb30b1e3abac1f0bd4d3a43aef69201a02b6dd55a6582e75af110dadb1","abstract_canon_sha256":"bd6e9d057dd5908ad93578229db9deee0361ec0eac8424a21f13233e45af29f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:17.535273Z","signature_b64":"OFnq+83u76tOgt4tcWPFCNJESV6JK9d8CkMBArJZdTpr89wlo1/7fXDLOBE6i7z0LRhcaGspad44FOIig0PMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8e9da0ff691c2ca87e25c748fbd77a195870162c68c1561a29ddfec238bd10f","last_reissued_at":"2026-07-05T02:24:17.534844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:17.534844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Andreas Savakis, Bruno Artacho","submitted_at":"2021-03-18T11:30:31Z","abstract_excerpt":"We propose OmniPose, a single-pass, end-to-end trainable framework, that achieves state-of-the-art results for multi-person pose estimation. Using a novel waterfall module, the OmniPose architecture leverages multi-scale feature representations that increase the effectiveness of backbone feature extractors, without the need for post-processing. OmniPose incorporates contextual information across scales and joint localization with Gaussian heatmap modulation at the multi-scale feature extractor to estimate human pose with state-of-the-art accuracy. The multi-scale representations, obtained by t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10180","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/2103.10180/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":"2103.10180","created_at":"2026-07-05T02:24:17.534910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.10180v1","created_at":"2026-07-05T02:24:17.534910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10180","created_at":"2026-07-05T02:24:17.534910+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DU5UD7WSHBM","created_at":"2026-07-05T02:24:17.534910+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DU5UD7WSHBMVB7C","created_at":"2026-07-05T02:24:17.534910+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DU5UD7W","created_at":"2026-07-05T02:24:17.534910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18944","citing_title":"Waterfall Transformer for Multi-person Pose Estimation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DU5UD7WSHBMVB7CLR2I7PLXUG","json":"https://pith.science/pith/7DU5UD7WSHBMVB7CLR2I7PLXUG.json","graph_json":"https://pith.science/api/pith-number/7DU5UD7WSHBMVB7CLR2I7PLXUG/graph.json","events_json":"https://pith.science/api/pith-number/7DU5UD7WSHBMVB7CLR2I7PLXUG/events.json","paper":"https://pith.science/paper/7DU5UD7W"},"agent_actions":{"view_html":"https://pith.science/pith/7DU5UD7WSHBMVB7CLR2I7PLXUG","download_json":"https://pith.science/pith/7DU5UD7WSHBMVB7CLR2I7PLXUG.json","view_paper":"https://pith.science/paper/7DU5UD7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.10180&json=true","fetch_graph":"https://pith.science/api/pith-number/7DU5UD7WSHBMVB7CLR2I7PLXUG/graph.json","fetch_events":"https://pith.science/api/pith-number/7DU5UD7WSHBMVB7CLR2I7PLXUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DU5UD7WSHBMVB7CLR2I7PLXUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DU5UD7WSHBMVB7CLR2I7PLXUG/action/storage_attestation","attest_author":"https://pith.science/pith/7DU5UD7WSHBMVB7CLR2I7PLXUG/action/author_attestation","sign_citation":"https://pith.science/pith/7DU5UD7WSHBMVB7CLR2I7PLXUG/action/citation_signature","submit_replication":"https://pith.science/pith/7DU5UD7WSHBMVB7CLR2I7PLXUG/action/replication_record"}},"created_at":"2026-07-05T02:24:17.534910+00:00","updated_at":"2026-07-05T02:24:17.534910+00:00"}