{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Q3L3M7CF5ZRKKVCQKUYMHBQEIC","short_pith_number":"pith:Q3L3M7CF","schema_version":"1.0","canonical_sha256":"86d7b67c45ee62a554505530c3860440b9c3560b746a78398f3b6f5e6b58d75b","source":{"kind":"arxiv","id":"2004.06239","version":4},"attestation_state":"computed","paper":{"title":"VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Hanyue Tu, Wenjun Zeng","submitted_at":"2020-04-13T23:50:01Z","abstract_excerpt":"We present an approach to estimate 3D poses of multiple people from multiple camera views. In contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete 2D pose estimations, we present an end-to-end solution which directly operates in the $3$D space, therefore avoids making incorrect decisions in the 2D space. To achieve this goal, the features in all camera views are warped and aggregated in a common 3D space, and fed into Cuboid Proposal Network (CPN) to coarsely localize all people. Then we propose Pose Regression Network (PRN) to est"},"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":"2004.06239","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T23:50:01Z","cross_cats_sorted":[],"title_canon_sha256":"897a0dbfdb417a79d3474eabdec6bc43951e4bdb3704e884dd071a4b53220d9e","abstract_canon_sha256":"64fe4733d6b6ab93b853350ca587a61c258d52834d3f6d4b3e5dd92c295a5d4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:04.982241Z","signature_b64":"RRPGmExj2rLJ+SQP3WWqF6kZYEz3TrhwUFi/wUW7JSDxLUxwmfceBrsVeRTA9rPtFY3pDCnVGHXua3PcX3M/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86d7b67c45ee62a554505530c3860440b9c3560b746a78398f3b6f5e6b58d75b","last_reissued_at":"2026-07-05T01:29:04.981830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:04.981830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Hanyue Tu, Wenjun Zeng","submitted_at":"2020-04-13T23:50:01Z","abstract_excerpt":"We present an approach to estimate 3D poses of multiple people from multiple camera views. In contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete 2D pose estimations, we present an end-to-end solution which directly operates in the $3$D space, therefore avoids making incorrect decisions in the 2D space. To achieve this goal, the features in all camera views are warped and aggregated in a common 3D space, and fed into Cuboid Proposal Network (CPN) to coarsely localize all people. Then we propose Pose Regression Network (PRN) to est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06239","kind":"arxiv","version":4},"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/2004.06239/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":"2004.06239","created_at":"2026-07-05T01:29:04.981885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.06239v4","created_at":"2026-07-05T01:29:04.981885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06239","created_at":"2026-07-05T01:29:04.981885+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3L3M7CF5ZRK","created_at":"2026-07-05T01:29:04.981885+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3L3M7CF5ZRKKVCQ","created_at":"2026-07-05T01:29:04.981885+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3L3M7CF","created_at":"2026-07-05T01:29:04.981885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03191","citing_title":"Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3L3M7CF5ZRKKVCQKUYMHBQEIC","json":"https://pith.science/pith/Q3L3M7CF5ZRKKVCQKUYMHBQEIC.json","graph_json":"https://pith.science/api/pith-number/Q3L3M7CF5ZRKKVCQKUYMHBQEIC/graph.json","events_json":"https://pith.science/api/pith-number/Q3L3M7CF5ZRKKVCQKUYMHBQEIC/events.json","paper":"https://pith.science/paper/Q3L3M7CF"},"agent_actions":{"view_html":"https://pith.science/pith/Q3L3M7CF5ZRKKVCQKUYMHBQEIC","download_json":"https://pith.science/pith/Q3L3M7CF5ZRKKVCQKUYMHBQEIC.json","view_paper":"https://pith.science/paper/Q3L3M7CF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.06239&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3L3M7CF5ZRKKVCQKUYMHBQEIC/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3L3M7CF5ZRKKVCQKUYMHBQEIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3L3M7CF5ZRKKVCQKUYMHBQEIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3L3M7CF5ZRKKVCQKUYMHBQEIC/action/storage_attestation","attest_author":"https://pith.science/pith/Q3L3M7CF5ZRKKVCQKUYMHBQEIC/action/author_attestation","sign_citation":"https://pith.science/pith/Q3L3M7CF5ZRKKVCQKUYMHBQEIC/action/citation_signature","submit_replication":"https://pith.science/pith/Q3L3M7CF5ZRKKVCQKUYMHBQEIC/action/replication_record"}},"created_at":"2026-07-05T01:29:04.981885+00:00","updated_at":"2026-07-05T01:29:04.981885+00:00"}