{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AZ2BEZI3THUCIXHP6KYEKC4MZA","short_pith_number":"pith:AZ2BEZI3","schema_version":"1.0","canonical_sha256":"067412651b99e8245ceff2b0450b8cc80816bfc6ecb5a5e38f8270dc693eea77","source":{"kind":"arxiv","id":"1908.07919","version":2},"attestation_state":"computed","paper":{"title":"Deep High-Resolution Representation Learning for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xiao, Borui Jiang, Chaorui Deng, Dong Liu, Jingdong Wang, Ke Sun, Mingkui Tan, Tianheng Cheng, Wenyu Liu, Xinggang Wang, Yadong Mu, Yang Zhao","submitted_at":"2019-08-20T10:47:46Z","abstract_excerpt":"High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions \\emph{in series} (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representat"},"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":"1908.07919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-20T10:47:46Z","cross_cats_sorted":[],"title_canon_sha256":"d880ba85aed616ebed3d2bcaae288a4316ef3e95585357613eb769ae6b4fc0a3","abstract_canon_sha256":"5ef49d809e0e246f5bcf8220926b104d33811408511439321e013ebb302b07dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:38.177603Z","signature_b64":"GTCS+bnyiVAz4Y1TJIeozNrxOQg09o9lDXGGjMpwOM24jVgPCl7CQ6XJL/WxC5f6wk4rlra4Q+JPsidV3J1PAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"067412651b99e8245ceff2b0450b8cc80816bfc6ecb5a5e38f8270dc693eea77","last_reissued_at":"2026-07-05T00:47:38.177103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:38.177103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep High-Resolution Representation Learning for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xiao, Borui Jiang, Chaorui Deng, Dong Liu, Jingdong Wang, Ke Sun, Mingkui Tan, Tianheng Cheng, Wenyu Liu, Xinggang Wang, Yadong Mu, Yang Zhao","submitted_at":"2019-08-20T10:47:46Z","abstract_excerpt":"High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions \\emph{in series} (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07919","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/1908.07919/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":"1908.07919","created_at":"2026-07-05T00:47:38.177162+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07919v2","created_at":"2026-07-05T00:47:38.177162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07919","created_at":"2026-07-05T00:47:38.177162+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZ2BEZI3THUC","created_at":"2026-07-05T00:47:38.177162+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZ2BEZI3THUCIXHP","created_at":"2026-07-05T00:47:38.177162+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZ2BEZI3","created_at":"2026-07-05T00:47:38.177162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17427","citing_title":"Impact of Hand Impairment and Occlusions on Hand Pose Estimation Accuracy in Augmented Reality Applications","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13364","citing_title":"VideoMDM: Towards 3D Human Motion Generation From 2D Supervision","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14805","citing_title":"From Boundaries to Semantics: Prompt-Guided Multi-Task Learning for Petrographic Thin-section Segmentation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZ2BEZI3THUCIXHP6KYEKC4MZA","json":"https://pith.science/pith/AZ2BEZI3THUCIXHP6KYEKC4MZA.json","graph_json":"https://pith.science/api/pith-number/AZ2BEZI3THUCIXHP6KYEKC4MZA/graph.json","events_json":"https://pith.science/api/pith-number/AZ2BEZI3THUCIXHP6KYEKC4MZA/events.json","paper":"https://pith.science/paper/AZ2BEZI3"},"agent_actions":{"view_html":"https://pith.science/pith/AZ2BEZI3THUCIXHP6KYEKC4MZA","download_json":"https://pith.science/pith/AZ2BEZI3THUCIXHP6KYEKC4MZA.json","view_paper":"https://pith.science/paper/AZ2BEZI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07919&json=true","fetch_graph":"https://pith.science/api/pith-number/AZ2BEZI3THUCIXHP6KYEKC4MZA/graph.json","fetch_events":"https://pith.science/api/pith-number/AZ2BEZI3THUCIXHP6KYEKC4MZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZ2BEZI3THUCIXHP6KYEKC4MZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZ2BEZI3THUCIXHP6KYEKC4MZA/action/storage_attestation","attest_author":"https://pith.science/pith/AZ2BEZI3THUCIXHP6KYEKC4MZA/action/author_attestation","sign_citation":"https://pith.science/pith/AZ2BEZI3THUCIXHP6KYEKC4MZA/action/citation_signature","submit_replication":"https://pith.science/pith/AZ2BEZI3THUCIXHP6KYEKC4MZA/action/replication_record"}},"created_at":"2026-07-05T00:47:38.177162+00:00","updated_at":"2026-07-05T00:47:38.177162+00:00"}