{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JX2ITWX5XWNSIXYX4RABXZQWZ4","short_pith_number":"pith:JX2ITWX5","schema_version":"1.0","canonical_sha256":"4df489dafdbd9b245f17e4401be616cf314a19dad29067911da215bcb91d3135","source":{"kind":"arxiv","id":"2509.07385","version":1},"attestation_state":"computed","paper":{"title":"Parse Graph-Based Visual-Language Interaction for Human Pose Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangming Shi, Shibang Liu, Xuemei Xie","submitted_at":"2025-09-09T04:41:35Z","abstract_excerpt":"Parse graphs boost human pose estimation (HPE) by integrating context and hierarchies, yet prior work mostly focuses on single modality modeling, ignoring the potential of multimodal fusion. Notably, language offers rich HPE priors like spatial relations for occluded scenes, but existing visual-language fusion via global feature integration weakens occluded region responses and causes alignment and location failures. To address this issue, we propose Parse Graph-based Visual-Language interaction (PGVL) with a core novel Guided Module (GM). In PGVL, low-level nodes focus on local features, maxi"},"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":"2509.07385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T04:41:35Z","cross_cats_sorted":[],"title_canon_sha256":"97d70f86494507b9ce7d5cafd8fdeff44750c956730d020b377298dc214e019e","abstract_canon_sha256":"df2ae8c7eba91da93789bc572f74bc0c78e294f395f27a2843df83c52b78e3ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:20.622201Z","signature_b64":"TiI9mo5I5GIrS2GvybqUUiFy9e8ChrjZelV6ABi0NoW9hVV16y0J4yN4auJrA+o1SYDtQj6fR3srM6RvwgjlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4df489dafdbd9b245f17e4401be616cf314a19dad29067911da215bcb91d3135","last_reissued_at":"2026-07-05T12:07:20.621722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:20.621722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parse Graph-Based Visual-Language Interaction for Human Pose Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangming Shi, Shibang Liu, Xuemei Xie","submitted_at":"2025-09-09T04:41:35Z","abstract_excerpt":"Parse graphs boost human pose estimation (HPE) by integrating context and hierarchies, yet prior work mostly focuses on single modality modeling, ignoring the potential of multimodal fusion. Notably, language offers rich HPE priors like spatial relations for occluded scenes, but existing visual-language fusion via global feature integration weakens occluded region responses and causes alignment and location failures. To address this issue, we propose Parse Graph-based Visual-Language interaction (PGVL) with a core novel Guided Module (GM). In PGVL, low-level nodes focus on local features, maxi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07385","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/2509.07385/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":"2509.07385","created_at":"2026-07-05T12:07:20.621781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.07385v1","created_at":"2026-07-05T12:07:20.621781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07385","created_at":"2026-07-05T12:07:20.621781+00:00"},{"alias_kind":"pith_short_12","alias_value":"JX2ITWX5XWNS","created_at":"2026-07-05T12:07:20.621781+00:00"},{"alias_kind":"pith_short_16","alias_value":"JX2ITWX5XWNSIXYX","created_at":"2026-07-05T12:07:20.621781+00:00"},{"alias_kind":"pith_short_8","alias_value":"JX2ITWX5","created_at":"2026-07-05T12:07:20.621781+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/JX2ITWX5XWNSIXYX4RABXZQWZ4","json":"https://pith.science/pith/JX2ITWX5XWNSIXYX4RABXZQWZ4.json","graph_json":"https://pith.science/api/pith-number/JX2ITWX5XWNSIXYX4RABXZQWZ4/graph.json","events_json":"https://pith.science/api/pith-number/JX2ITWX5XWNSIXYX4RABXZQWZ4/events.json","paper":"https://pith.science/paper/JX2ITWX5"},"agent_actions":{"view_html":"https://pith.science/pith/JX2ITWX5XWNSIXYX4RABXZQWZ4","download_json":"https://pith.science/pith/JX2ITWX5XWNSIXYX4RABXZQWZ4.json","view_paper":"https://pith.science/paper/JX2ITWX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.07385&json=true","fetch_graph":"https://pith.science/api/pith-number/JX2ITWX5XWNSIXYX4RABXZQWZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/JX2ITWX5XWNSIXYX4RABXZQWZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JX2ITWX5XWNSIXYX4RABXZQWZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JX2ITWX5XWNSIXYX4RABXZQWZ4/action/storage_attestation","attest_author":"https://pith.science/pith/JX2ITWX5XWNSIXYX4RABXZQWZ4/action/author_attestation","sign_citation":"https://pith.science/pith/JX2ITWX5XWNSIXYX4RABXZQWZ4/action/citation_signature","submit_replication":"https://pith.science/pith/JX2ITWX5XWNSIXYX4RABXZQWZ4/action/replication_record"}},"created_at":"2026-07-05T12:07:20.621781+00:00","updated_at":"2026-07-05T12:07:20.621781+00:00"}