{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3GALTEC5GIWOZR6L32ENGADECV","short_pith_number":"pith:3GALTEC5","schema_version":"1.0","canonical_sha256":"d980b9905d322cecc7cbde88d300641564ceddc808835e85b2e5c3e70faa15b0","source":{"kind":"arxiv","id":"2411.19824","version":4},"attestation_state":"computed","paper":{"title":"SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Su, Jiajun Su, Xiaoxuan Ma, Yizhou Wang","submitted_at":"2024-11-29T16:34:46Z","abstract_excerpt":"We propose a one-stage framework for real-time multi-person 3D human mesh estimation from a single RGB image. While current one-stage methods, which follow a DETR-style pipeline, achieve state-of-the-art (SOTA) performance with high-resolution inputs, we observe that this particularly benefits the estimation of individuals in smaller scales of the image (e.g., those far from the camera), but at the cost of significantly increased computation overhead. To address this, we introduce scale-adaptive tokens that are dynamically adjusted based on the relative scale of each individual in the image wi"},"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":"2411.19824","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T16:34:46Z","cross_cats_sorted":[],"title_canon_sha256":"aa0f143123c3c2c3ee20a3b088c6f74665f866a536d45571f19ace68c63b29b3","abstract_canon_sha256":"df51ea5ca685479386c78169cb0c8e70b9b98678b926315860bda25dd2adcff0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:11.519992Z","signature_b64":"Er5MxMqLrxv5Qw12yb+T2A1ZvubcdjGkYToUJumd20Zwt3NNLFn88y0xoyobFEcVLBbRHmi7SZisrVTbx5jkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d980b9905d322cecc7cbde88d300641564ceddc808835e85b2e5c3e70faa15b0","last_reissued_at":"2026-07-05T10:49:11.519500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:11.519500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Su, Jiajun Su, Xiaoxuan Ma, Yizhou Wang","submitted_at":"2024-11-29T16:34:46Z","abstract_excerpt":"We propose a one-stage framework for real-time multi-person 3D human mesh estimation from a single RGB image. While current one-stage methods, which follow a DETR-style pipeline, achieve state-of-the-art (SOTA) performance with high-resolution inputs, we observe that this particularly benefits the estimation of individuals in smaller scales of the image (e.g., those far from the camera), but at the cost of significantly increased computation overhead. To address this, we introduce scale-adaptive tokens that are dynamically adjusted based on the relative scale of each individual in the image wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19824","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/2411.19824/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":"2411.19824","created_at":"2026-07-05T10:49:11.519560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19824v4","created_at":"2026-07-05T10:49:11.519560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19824","created_at":"2026-07-05T10:49:11.519560+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GALTEC5GIWO","created_at":"2026-07-05T10:49:11.519560+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GALTEC5GIWOZR6L","created_at":"2026-07-05T10:49:11.519560+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GALTEC5","created_at":"2026-07-05T10:49:11.519560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04554","citing_title":"InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GALTEC5GIWOZR6L32ENGADECV","json":"https://pith.science/pith/3GALTEC5GIWOZR6L32ENGADECV.json","graph_json":"https://pith.science/api/pith-number/3GALTEC5GIWOZR6L32ENGADECV/graph.json","events_json":"https://pith.science/api/pith-number/3GALTEC5GIWOZR6L32ENGADECV/events.json","paper":"https://pith.science/paper/3GALTEC5"},"agent_actions":{"view_html":"https://pith.science/pith/3GALTEC5GIWOZR6L32ENGADECV","download_json":"https://pith.science/pith/3GALTEC5GIWOZR6L32ENGADECV.json","view_paper":"https://pith.science/paper/3GALTEC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19824&json=true","fetch_graph":"https://pith.science/api/pith-number/3GALTEC5GIWOZR6L32ENGADECV/graph.json","fetch_events":"https://pith.science/api/pith-number/3GALTEC5GIWOZR6L32ENGADECV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GALTEC5GIWOZR6L32ENGADECV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GALTEC5GIWOZR6L32ENGADECV/action/storage_attestation","attest_author":"https://pith.science/pith/3GALTEC5GIWOZR6L32ENGADECV/action/author_attestation","sign_citation":"https://pith.science/pith/3GALTEC5GIWOZR6L32ENGADECV/action/citation_signature","submit_replication":"https://pith.science/pith/3GALTEC5GIWOZR6L32ENGADECV/action/replication_record"}},"created_at":"2026-07-05T10:49:11.519560+00:00","updated_at":"2026-07-05T10:49:11.519560+00:00"}