{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QPPIQ63UDACVPZI6YNYIBTWOX5","short_pith_number":"pith:QPPIQ63U","schema_version":"1.0","canonical_sha256":"83de887b74180557e51ec37080cecebf4a3d2374f56af0b64663fb679282a709","source":{"kind":"arxiv","id":"1907.00837","version":2},"attestation_state":"computed","paper":{"title":"XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Christian Theobalt, Dushyant Mehta, Franziska Mueller, Gerard Pons-Moll, Hans-Peter Seidel, Helge Rhodin, Mohamed Elgharib, Oleksandr Sotnychenko, Pascal Fua, Weipeng Xu","submitted_at":"2019-07-01T14:59:02Z","abstract_excerpt":"We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals.We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for"},"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":"1907.00837","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-01T14:59:02Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"0065e127c0c723612eaa7be72e818e70d26c1526713dee8fb154319819088cd5","abstract_canon_sha256":"cc01c3ff2061e04a3d7bb54cc0df0bb0adf0c191239960ea4d55f68b4094af6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:22.072873Z","signature_b64":"qyrXfPK5TEeiMNPQM2IT0Rcr7pqGungAHn7rOyQh7333YM1u4LmLDAHrWrphR8AxpJEUhbxL2fw3aNkv9ozXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83de887b74180557e51ec37080cecebf4a3d2374f56af0b64663fb679282a709","last_reissued_at":"2026-07-05T00:59:22.072400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:22.072400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Christian Theobalt, Dushyant Mehta, Franziska Mueller, Gerard Pons-Moll, Hans-Peter Seidel, Helge Rhodin, Mohamed Elgharib, Oleksandr Sotnychenko, Pascal Fua, Weipeng Xu","submitted_at":"2019-07-01T14:59:02Z","abstract_excerpt":"We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals.We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00837","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/1907.00837/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":"1907.00837","created_at":"2026-07-05T00:59:22.072457+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.00837v2","created_at":"2026-07-05T00:59:22.072457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00837","created_at":"2026-07-05T00:59:22.072457+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPPIQ63UDACV","created_at":"2026-07-05T00:59:22.072457+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPPIQ63UDACVPZI6","created_at":"2026-07-05T00:59:22.072457+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPPIQ63U","created_at":"2026-07-05T00:59:22.072457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.04781","citing_title":"Predicting 3D Human Dynamics from Video","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPPIQ63UDACVPZI6YNYIBTWOX5","json":"https://pith.science/pith/QPPIQ63UDACVPZI6YNYIBTWOX5.json","graph_json":"https://pith.science/api/pith-number/QPPIQ63UDACVPZI6YNYIBTWOX5/graph.json","events_json":"https://pith.science/api/pith-number/QPPIQ63UDACVPZI6YNYIBTWOX5/events.json","paper":"https://pith.science/paper/QPPIQ63U"},"agent_actions":{"view_html":"https://pith.science/pith/QPPIQ63UDACVPZI6YNYIBTWOX5","download_json":"https://pith.science/pith/QPPIQ63UDACVPZI6YNYIBTWOX5.json","view_paper":"https://pith.science/paper/QPPIQ63U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.00837&json=true","fetch_graph":"https://pith.science/api/pith-number/QPPIQ63UDACVPZI6YNYIBTWOX5/graph.json","fetch_events":"https://pith.science/api/pith-number/QPPIQ63UDACVPZI6YNYIBTWOX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPPIQ63UDACVPZI6YNYIBTWOX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPPIQ63UDACVPZI6YNYIBTWOX5/action/storage_attestation","attest_author":"https://pith.science/pith/QPPIQ63UDACVPZI6YNYIBTWOX5/action/author_attestation","sign_citation":"https://pith.science/pith/QPPIQ63UDACVPZI6YNYIBTWOX5/action/citation_signature","submit_replication":"https://pith.science/pith/QPPIQ63UDACVPZI6YNYIBTWOX5/action/replication_record"}},"created_at":"2026-07-05T00:59:22.072457+00:00","updated_at":"2026-07-05T00:59:22.072457+00:00"}