{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BL7GNTEXKR663KSYLZ2BH3QVWU","short_pith_number":"pith:BL7GNTEX","schema_version":"1.0","canonical_sha256":"0afe66cc97547dedaa585e7413ee15b50e4c1ef8049caf9932db5cc7b4ed3fc1","source":{"kind":"arxiv","id":"2310.20695","version":1},"attestation_state":"computed","paper":{"title":"HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Errui Ding, Fei Wu, Hao Zhou, Jian Wang, Jingdong Wang, Junkun Yuan, Junyu Han, Kun Kuang, Kun Yao, Lanfen Lin, Shaofeng Zhang, Sifan Long, Xinyu Zhang, Zhiyin Shao, Zhongwei Qiu","submitted_at":"2023-10-31T17:56:11Z","abstract_excerpt":"Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting the MIM training strategy, we reveal that human structure priors offer significant potential. Motivated by this insight, we further incorporate an intuitive human structure prior - human parts - into pre-training. Specifically, we employ this prior to guide the mask sampling process. Image patches, corresponding to human part regions, have high priority to be masked out. This encourages the model to concentrate more"},"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":"2310.20695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T17:56:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7cfac5197bc4dd40b68910e18ac734b2429a082126f31587c7633850fc6821ac","abstract_canon_sha256":"5538ad82bde9edd965a152776eabc2604bfcbb5d36b4ce863381119b16666b4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:34.058105Z","signature_b64":"xvQa7SG4C5jBu1ydYjvVoa3cpDN2ao+Qy0Lc+KAnPbZXP3D79rM+1ntzodP0hQfNiw5I0EbasmmIwRs8NA7VCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0afe66cc97547dedaa585e7413ee15b50e4c1ef8049caf9932db5cc7b4ed3fc1","last_reissued_at":"2026-07-05T07:07:34.056916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:34.056916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Errui Ding, Fei Wu, Hao Zhou, Jian Wang, Jingdong Wang, Junkun Yuan, Junyu Han, Kun Kuang, Kun Yao, Lanfen Lin, Shaofeng Zhang, Sifan Long, Xinyu Zhang, Zhiyin Shao, Zhongwei Qiu","submitted_at":"2023-10-31T17:56:11Z","abstract_excerpt":"Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting the MIM training strategy, we reveal that human structure priors offer significant potential. Motivated by this insight, we further incorporate an intuitive human structure prior - human parts - into pre-training. Specifically, we employ this prior to guide the mask sampling process. Image patches, corresponding to human part regions, have high priority to be masked out. This encourages the model to concentrate more"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20695","kind":"arxiv","version":1},"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/2310.20695/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":"2310.20695","created_at":"2026-07-05T07:07:34.057533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.20695v1","created_at":"2026-07-05T07:07:34.057533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20695","created_at":"2026-07-05T07:07:34.057533+00:00"},{"alias_kind":"pith_short_12","alias_value":"BL7GNTEXKR66","created_at":"2026-07-05T07:07:34.057533+00:00"},{"alias_kind":"pith_short_16","alias_value":"BL7GNTEXKR663KSY","created_at":"2026-07-05T07:07:34.057533+00:00"},{"alias_kind":"pith_short_8","alias_value":"BL7GNTEX","created_at":"2026-07-05T07:07:34.057533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BL7GNTEXKR663KSYLZ2BH3QVWU","json":"https://pith.science/pith/BL7GNTEXKR663KSYLZ2BH3QVWU.json","graph_json":"https://pith.science/api/pith-number/BL7GNTEXKR663KSYLZ2BH3QVWU/graph.json","events_json":"https://pith.science/api/pith-number/BL7GNTEXKR663KSYLZ2BH3QVWU/events.json","paper":"https://pith.science/paper/BL7GNTEX"},"agent_actions":{"view_html":"https://pith.science/pith/BL7GNTEXKR663KSYLZ2BH3QVWU","download_json":"https://pith.science/pith/BL7GNTEXKR663KSYLZ2BH3QVWU.json","view_paper":"https://pith.science/paper/BL7GNTEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.20695&json=true","fetch_graph":"https://pith.science/api/pith-number/BL7GNTEXKR663KSYLZ2BH3QVWU/graph.json","fetch_events":"https://pith.science/api/pith-number/BL7GNTEXKR663KSYLZ2BH3QVWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BL7GNTEXKR663KSYLZ2BH3QVWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BL7GNTEXKR663KSYLZ2BH3QVWU/action/storage_attestation","attest_author":"https://pith.science/pith/BL7GNTEXKR663KSYLZ2BH3QVWU/action/author_attestation","sign_citation":"https://pith.science/pith/BL7GNTEXKR663KSYLZ2BH3QVWU/action/citation_signature","submit_replication":"https://pith.science/pith/BL7GNTEXKR663KSYLZ2BH3QVWU/action/replication_record"}},"created_at":"2026-07-05T07:07:34.057533+00:00","updated_at":"2026-07-05T07:07:34.057533+00:00"}