{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KM35RKWK36QVGX7CZDCO5ZF7M6","short_pith_number":"pith:KM35RKWK","schema_version":"1.0","canonical_sha256":"5337d8aacadfa1535fe2c8c4eee4bf67a4f4409c6f7e8c4a2d77b7c4edcfaad8","source":{"kind":"arxiv","id":"2002.03923","version":2},"attestation_state":"computed","paper":{"title":"6DoF Object Pose Estimation via Differentiable Proxy Voting Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongdong Li, Piotr Koniusz, Xin Yu, Zheyu Zhuang","submitted_at":"2020-02-10T16:33:33Z","abstract_excerpt":"Estimating a 6DOF object pose from a single image is very challenging due to occlusions or textureless appearances. Vector-field based keypoint voting has demonstrated its effectiveness and superiority on tackling those issues. However, direct regression of vector-fields neglects that the distances between pixels and keypoints also affect the deviations of hypotheses dramatically. In other words, small errors in direction vectors may generate severely deviated hypotheses when pixels are far away from a keypoint. In this paper, we aim to reduce such errors by incorporating the distances between"},"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":"2002.03923","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-10T16:33:33Z","cross_cats_sorted":[],"title_canon_sha256":"209d8f26fab34d2b8592c7b8522a63977ca88ba655050e7fb99915149802a7e0","abstract_canon_sha256":"82c90ac49d2c974e47e6e22800a067c0c778aea385a34121a2f52b23191e1b5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:16.188975Z","signature_b64":"9lFfBiTsdNd47CLb7hXa3AvBebCfn6dYcs+k420OHXVMahRyynOTPDUfTLYNQwMHg6LHQFp8ZevIrSop1pi3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5337d8aacadfa1535fe2c8c4eee4bf67a4f4409c6f7e8c4a2d77b7c4edcfaad8","last_reissued_at":"2026-07-05T01:00:16.188537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:16.188537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"6DoF Object Pose Estimation via Differentiable Proxy Voting Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongdong Li, Piotr Koniusz, Xin Yu, Zheyu Zhuang","submitted_at":"2020-02-10T16:33:33Z","abstract_excerpt":"Estimating a 6DOF object pose from a single image is very challenging due to occlusions or textureless appearances. Vector-field based keypoint voting has demonstrated its effectiveness and superiority on tackling those issues. However, direct regression of vector-fields neglects that the distances between pixels and keypoints also affect the deviations of hypotheses dramatically. In other words, small errors in direction vectors may generate severely deviated hypotheses when pixels are far away from a keypoint. In this paper, we aim to reduce such errors by incorporating the distances between"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03923","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/2002.03923/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":"2002.03923","created_at":"2026-07-05T01:00:16.188593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.03923v2","created_at":"2026-07-05T01:00:16.188593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03923","created_at":"2026-07-05T01:00:16.188593+00:00"},{"alias_kind":"pith_short_12","alias_value":"KM35RKWK36QV","created_at":"2026-07-05T01:00:16.188593+00:00"},{"alias_kind":"pith_short_16","alias_value":"KM35RKWK36QVGX7C","created_at":"2026-07-05T01:00:16.188593+00:00"},{"alias_kind":"pith_short_8","alias_value":"KM35RKWK","created_at":"2026-07-05T01:00:16.188593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14358","citing_title":"Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimation","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KM35RKWK36QVGX7CZDCO5ZF7M6","json":"https://pith.science/pith/KM35RKWK36QVGX7CZDCO5ZF7M6.json","graph_json":"https://pith.science/api/pith-number/KM35RKWK36QVGX7CZDCO5ZF7M6/graph.json","events_json":"https://pith.science/api/pith-number/KM35RKWK36QVGX7CZDCO5ZF7M6/events.json","paper":"https://pith.science/paper/KM35RKWK"},"agent_actions":{"view_html":"https://pith.science/pith/KM35RKWK36QVGX7CZDCO5ZF7M6","download_json":"https://pith.science/pith/KM35RKWK36QVGX7CZDCO5ZF7M6.json","view_paper":"https://pith.science/paper/KM35RKWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.03923&json=true","fetch_graph":"https://pith.science/api/pith-number/KM35RKWK36QVGX7CZDCO5ZF7M6/graph.json","fetch_events":"https://pith.science/api/pith-number/KM35RKWK36QVGX7CZDCO5ZF7M6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KM35RKWK36QVGX7CZDCO5ZF7M6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KM35RKWK36QVGX7CZDCO5ZF7M6/action/storage_attestation","attest_author":"https://pith.science/pith/KM35RKWK36QVGX7CZDCO5ZF7M6/action/author_attestation","sign_citation":"https://pith.science/pith/KM35RKWK36QVGX7CZDCO5ZF7M6/action/citation_signature","submit_replication":"https://pith.science/pith/KM35RKWK36QVGX7CZDCO5ZF7M6/action/replication_record"}},"created_at":"2026-07-05T01:00:16.188593+00:00","updated_at":"2026-07-05T01:00:16.188593+00:00"}