{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AQAUEQY6G2ZJ6HTUFRBFXECAY2","short_pith_number":"pith:AQAUEQY6","schema_version":"1.0","canonical_sha256":"040142431e36b29f1e742c425b9040c699c7eecf7435e0abb3fc39f28d884336","source":{"kind":"arxiv","id":"2310.08530","version":2},"attestation_state":"computed","paper":{"title":"X-Pose: Detecting Any Keypoints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Jie Yang, Lei Zhang, Ruimao Zhang","submitted_at":"2023-10-12T17:22:58Z","abstract_excerpt":"This work aims to address an advanced keypoint detection problem: how to accurately detect any keypoints in complex real-world scenarios, which involves massive, messy, and open-ended objects as well as their associated keypoints definitions. Current high-performance keypoint detectors often fail to tackle this problem due to their two-stage schemes, under-explored prompt designs, and limited training data. To bridge the gap, we propose X-Pose, a novel end-to-end framework with multi-modal (i.e., visual, textual, or their combinations) prompts to detect multi-object keypoints for any articulat"},"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":"2310.08530","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-12T17:22:58Z","cross_cats_sorted":[],"title_canon_sha256":"323560359dd4d3ec291f46f3d7bb384f7eedc958204873c610e91fe11963d003","abstract_canon_sha256":"2d84e05e82deb7b610e317a99b3e1d75c50e4cc20a2a7e999b7ab3137216d6fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:47.913589Z","signature_b64":"FdL/a7kWN5AmCnmhPDx1lhrkitoIv7BC8LmDadvVy+LckOIoLEOyQ0YB8FwP7aI62zXkYfHkoYIOR5+4VgvdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"040142431e36b29f1e742c425b9040c699c7eecf7435e0abb3fc39f28d884336","last_reissued_at":"2026-07-05T08:44:47.912962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:47.912962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-Pose: Detecting Any Keypoints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Jie Yang, Lei Zhang, Ruimao Zhang","submitted_at":"2023-10-12T17:22:58Z","abstract_excerpt":"This work aims to address an advanced keypoint detection problem: how to accurately detect any keypoints in complex real-world scenarios, which involves massive, messy, and open-ended objects as well as their associated keypoints definitions. Current high-performance keypoint detectors often fail to tackle this problem due to their two-stage schemes, under-explored prompt designs, and limited training data. To bridge the gap, we propose X-Pose, a novel end-to-end framework with multi-modal (i.e., visual, textual, or their combinations) prompts to detect multi-object keypoints for any articulat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08530","kind":"arxiv","version":2},"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/2310.08530/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":"2310.08530","created_at":"2026-07-05T08:44:47.913051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08530v2","created_at":"2026-07-05T08:44:47.913051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08530","created_at":"2026-07-05T08:44:47.913051+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQAUEQY6G2ZJ","created_at":"2026-07-05T08:44:47.913051+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQAUEQY6G2ZJ6HTU","created_at":"2026-07-05T08:44:47.913051+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQAUEQY6","created_at":"2026-07-05T08:44:47.913051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQAUEQY6G2ZJ6HTUFRBFXECAY2","json":"https://pith.science/pith/AQAUEQY6G2ZJ6HTUFRBFXECAY2.json","graph_json":"https://pith.science/api/pith-number/AQAUEQY6G2ZJ6HTUFRBFXECAY2/graph.json","events_json":"https://pith.science/api/pith-number/AQAUEQY6G2ZJ6HTUFRBFXECAY2/events.json","paper":"https://pith.science/paper/AQAUEQY6"},"agent_actions":{"view_html":"https://pith.science/pith/AQAUEQY6G2ZJ6HTUFRBFXECAY2","download_json":"https://pith.science/pith/AQAUEQY6G2ZJ6HTUFRBFXECAY2.json","view_paper":"https://pith.science/paper/AQAUEQY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08530&json=true","fetch_graph":"https://pith.science/api/pith-number/AQAUEQY6G2ZJ6HTUFRBFXECAY2/graph.json","fetch_events":"https://pith.science/api/pith-number/AQAUEQY6G2ZJ6HTUFRBFXECAY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQAUEQY6G2ZJ6HTUFRBFXECAY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQAUEQY6G2ZJ6HTUFRBFXECAY2/action/storage_attestation","attest_author":"https://pith.science/pith/AQAUEQY6G2ZJ6HTUFRBFXECAY2/action/author_attestation","sign_citation":"https://pith.science/pith/AQAUEQY6G2ZJ6HTUFRBFXECAY2/action/citation_signature","submit_replication":"https://pith.science/pith/AQAUEQY6G2ZJ6HTUFRBFXECAY2/action/replication_record"}},"created_at":"2026-07-05T08:44:47.913051+00:00","updated_at":"2026-07-05T08:44:47.913051+00:00"}