{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZT4TNIC3Y6LZQFJWBQDMFLGFOB","short_pith_number":"pith:ZT4TNIC3","schema_version":"1.0","canonical_sha256":"ccf936a05bc7979815360c06c2acc570632aa164c011671d49f5fc285e13ff68","source":{"kind":"arxiv","id":"2402.14654","version":2},"attestation_state":"computed","paper":{"title":"Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabien Baradel, Gr\\'egory Rogez, Matthieu Armando, Philippe Weinzaepfel, Romain Br\\'egier, Salma Galaaoui, Thomas Lucas","submitted_at":"2024-02-22T16:05:13Z","abstract_excerpt":"We present Multi-HMR, a strong sigle-shot model for multi-person 3D human mesh recovery from a single RGB image. Predictions encompass the whole body, i.e., including hands and facial expressions, using the SMPL-X parametric model and 3D location in the camera coordinate system. Our model detects people by predicting coarse 2D heatmaps of person locations, using features produced by a standard Vision Transformer (ViT) backbone. It then predicts their whole-body pose, shape and 3D location using a new cross-attention module called the Human Prediction Head (HPH), with one query attending to the"},"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":"2402.14654","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T16:05:13Z","cross_cats_sorted":[],"title_canon_sha256":"3eda94cc15063da86671226b65c4f02b14e77e4ed81acd94576f803c5174f7d5","abstract_canon_sha256":"a16e7eb440236124c532e6d68c11d5c43b81ac460bcbcf0590a7c08402d81097"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:49.996466Z","signature_b64":"1IsCh1pP3mRX9uqVxEaOS5lMKKVBsnkit/qJvGrWGxaRi4akkj8rcu8JerSyyQ03IOqLGCLFiihZde045DAlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccf936a05bc7979815360c06c2acc570632aa164c011671d49f5fc285e13ff68","last_reissued_at":"2026-07-05T08:47:49.996067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:49.996067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabien Baradel, Gr\\'egory Rogez, Matthieu Armando, Philippe Weinzaepfel, Romain Br\\'egier, Salma Galaaoui, Thomas Lucas","submitted_at":"2024-02-22T16:05:13Z","abstract_excerpt":"We present Multi-HMR, a strong sigle-shot model for multi-person 3D human mesh recovery from a single RGB image. Predictions encompass the whole body, i.e., including hands and facial expressions, using the SMPL-X parametric model and 3D location in the camera coordinate system. Our model detects people by predicting coarse 2D heatmaps of person locations, using features produced by a standard Vision Transformer (ViT) backbone. It then predicts their whole-body pose, shape and 3D location using a new cross-attention module called the Human Prediction Head (HPH), with one query attending to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14654","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/2402.14654/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":"2402.14654","created_at":"2026-07-05T08:47:49.996122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14654v2","created_at":"2026-07-05T08:47:49.996122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14654","created_at":"2026-07-05T08:47:49.996122+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZT4TNIC3Y6LZ","created_at":"2026-07-05T08:47:49.996122+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZT4TNIC3Y6LZQFJW","created_at":"2026-07-05T08:47:49.996122+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZT4TNIC3","created_at":"2026-07-05T08:47:49.996122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13854","citing_title":"Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recovery","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZT4TNIC3Y6LZQFJWBQDMFLGFOB","json":"https://pith.science/pith/ZT4TNIC3Y6LZQFJWBQDMFLGFOB.json","graph_json":"https://pith.science/api/pith-number/ZT4TNIC3Y6LZQFJWBQDMFLGFOB/graph.json","events_json":"https://pith.science/api/pith-number/ZT4TNIC3Y6LZQFJWBQDMFLGFOB/events.json","paper":"https://pith.science/paper/ZT4TNIC3"},"agent_actions":{"view_html":"https://pith.science/pith/ZT4TNIC3Y6LZQFJWBQDMFLGFOB","download_json":"https://pith.science/pith/ZT4TNIC3Y6LZQFJWBQDMFLGFOB.json","view_paper":"https://pith.science/paper/ZT4TNIC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14654&json=true","fetch_graph":"https://pith.science/api/pith-number/ZT4TNIC3Y6LZQFJWBQDMFLGFOB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZT4TNIC3Y6LZQFJWBQDMFLGFOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZT4TNIC3Y6LZQFJWBQDMFLGFOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZT4TNIC3Y6LZQFJWBQDMFLGFOB/action/storage_attestation","attest_author":"https://pith.science/pith/ZT4TNIC3Y6LZQFJWBQDMFLGFOB/action/author_attestation","sign_citation":"https://pith.science/pith/ZT4TNIC3Y6LZQFJWBQDMFLGFOB/action/citation_signature","submit_replication":"https://pith.science/pith/ZT4TNIC3Y6LZQFJWBQDMFLGFOB/action/replication_record"}},"created_at":"2026-07-05T08:47:49.996122+00:00","updated_at":"2026-07-05T08:47:49.996122+00:00"}