{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2MHAEJSN2WDOPLGNSYTMJF6N4S","short_pith_number":"pith:2MHAEJSN","schema_version":"1.0","canonical_sha256":"d30e02264dd586e7accd9626c497cde4a39890ba81f871c7014f4f03e053193c","source":{"kind":"arxiv","id":"2309.13242","version":2},"attestation_state":"computed","paper":{"title":"UniHead: Unifying Multi-Perception for Detection Heads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hantao Zhou, Haoran Duan, Rui Yang, Runze Hu, Xiu Li, Yachao Zhang, Yawen Huang, Yefeng Zheng","submitted_at":"2023-09-23T03:22:48Z","abstract_excerpt":"The detection head constitutes a pivotal component within object detectors, tasked with executing both classification and localization functions. Regrettably, the commonly used parallel head often lacks omni perceptual capabilities, such as deformation perception, global perception and cross-task perception. Despite numerous methods attempting to enhance these abilities from a single aspect, achieving a comprehensive and unified solution remains a significant challenge. In response to this challenge, we develop an innovative detection head, termed UniHead, to unify three perceptual abilities s"},"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":"2309.13242","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-23T03:22:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c52a0d36cb99cdfc6c0c2f494adee95e7352b103ba749774eb1b4407c02369a8","abstract_canon_sha256":"5a39c832816ae617383cf36ed27d2697abe618e28cb57af4597c517a3758fa77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:17.456796Z","signature_b64":"l1TyxX5Lc4PRYYXHtO6g/+XQdXizktzkc6gMnzorVNgrvlOAelYysb4GrmxxKClSnkcHbz0pwbL7Tn1Gp8DzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d30e02264dd586e7accd9626c497cde4a39890ba81f871c7014f4f03e053193c","last_reissued_at":"2026-07-05T08:29:17.456274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:17.456274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniHead: Unifying Multi-Perception for Detection Heads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hantao Zhou, Haoran Duan, Rui Yang, Runze Hu, Xiu Li, Yachao Zhang, Yawen Huang, Yefeng Zheng","submitted_at":"2023-09-23T03:22:48Z","abstract_excerpt":"The detection head constitutes a pivotal component within object detectors, tasked with executing both classification and localization functions. Regrettably, the commonly used parallel head often lacks omni perceptual capabilities, such as deformation perception, global perception and cross-task perception. Despite numerous methods attempting to enhance these abilities from a single aspect, achieving a comprehensive and unified solution remains a significant challenge. In response to this challenge, we develop an innovative detection head, termed UniHead, to unify three perceptual abilities s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13242","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/2309.13242/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":"2309.13242","created_at":"2026-07-05T08:29:17.456343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13242v2","created_at":"2026-07-05T08:29:17.456343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13242","created_at":"2026-07-05T08:29:17.456343+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MHAEJSN2WDO","created_at":"2026-07-05T08:29:17.456343+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MHAEJSN2WDOPLGN","created_at":"2026-07-05T08:29:17.456343+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MHAEJSN","created_at":"2026-07-05T08:29:17.456343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01822","citing_title":"Hierarchically Decoupled Mixture-of-Experts for Robust Traffic Sign Recognition in Complex Driving Scenarios","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MHAEJSN2WDOPLGNSYTMJF6N4S","json":"https://pith.science/pith/2MHAEJSN2WDOPLGNSYTMJF6N4S.json","graph_json":"https://pith.science/api/pith-number/2MHAEJSN2WDOPLGNSYTMJF6N4S/graph.json","events_json":"https://pith.science/api/pith-number/2MHAEJSN2WDOPLGNSYTMJF6N4S/events.json","paper":"https://pith.science/paper/2MHAEJSN"},"agent_actions":{"view_html":"https://pith.science/pith/2MHAEJSN2WDOPLGNSYTMJF6N4S","download_json":"https://pith.science/pith/2MHAEJSN2WDOPLGNSYTMJF6N4S.json","view_paper":"https://pith.science/paper/2MHAEJSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13242&json=true","fetch_graph":"https://pith.science/api/pith-number/2MHAEJSN2WDOPLGNSYTMJF6N4S/graph.json","fetch_events":"https://pith.science/api/pith-number/2MHAEJSN2WDOPLGNSYTMJF6N4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MHAEJSN2WDOPLGNSYTMJF6N4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MHAEJSN2WDOPLGNSYTMJF6N4S/action/storage_attestation","attest_author":"https://pith.science/pith/2MHAEJSN2WDOPLGNSYTMJF6N4S/action/author_attestation","sign_citation":"https://pith.science/pith/2MHAEJSN2WDOPLGNSYTMJF6N4S/action/citation_signature","submit_replication":"https://pith.science/pith/2MHAEJSN2WDOPLGNSYTMJF6N4S/action/replication_record"}},"created_at":"2026-07-05T08:29:17.456343+00:00","updated_at":"2026-07-05T08:29:17.456343+00:00"}