{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:I5FH6LNKU326KGIJYS3LJSANSN","short_pith_number":"pith:I5FH6LNK","schema_version":"1.0","canonical_sha256":"474a7f2daaa6f5e51909c4b6b4c80d934df509c47e7429ebc532c4d7d3470e94","source":{"kind":"arxiv","id":"1603.01249","version":3},"attestation_state":"computed","paper":{"title":"HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rajeev Ranjan, Rama Chellappa, Vishal M. Patel","submitted_at":"2016-03-03T20:30:53Z","abstract_excerpt":"We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance"},"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":"1603.01249","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-03T20:30:53Z","cross_cats_sorted":[],"title_canon_sha256":"9a94ab3c33d37e6043933b1ada0da1380967d1a934f55c037e7fc604d573cfeb","abstract_canon_sha256":"da9a9c07e2b976f49c0e48d48d0a89df908b91c7928bbb2836ba75a8a76823e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:41.397759Z","signature_b64":"XtYzh2q3Udcz3gHMxzCVovZp4T1HSP5fJP7Ih/xaf7re6P6VaINRI2gODikJqmG7xNANT0samVyvgjg1P1lpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"474a7f2daaa6f5e51909c4b6b4c80d934df509c47e7429ebc532c4d7d3470e94","last_reissued_at":"2026-05-18T00:28:41.397016Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:41.397016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rajeev Ranjan, Rama Chellappa, Vishal M. Patel","submitted_at":"2016-03-03T20:30:53Z","abstract_excerpt":"We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.01249","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1603.01249","created_at":"2026-05-18T00:28:41.397120+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.01249v3","created_at":"2026-05-18T00:28:41.397120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.01249","created_at":"2026-05-18T00:28:41.397120+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5FH6LNKU326","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5FH6LNKU326KGIJ","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5FH6LNK","created_at":"2026-05-18T12:30:22.444734+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/I5FH6LNKU326KGIJYS3LJSANSN","json":"https://pith.science/pith/I5FH6LNKU326KGIJYS3LJSANSN.json","graph_json":"https://pith.science/api/pith-number/I5FH6LNKU326KGIJYS3LJSANSN/graph.json","events_json":"https://pith.science/api/pith-number/I5FH6LNKU326KGIJYS3LJSANSN/events.json","paper":"https://pith.science/paper/I5FH6LNK"},"agent_actions":{"view_html":"https://pith.science/pith/I5FH6LNKU326KGIJYS3LJSANSN","download_json":"https://pith.science/pith/I5FH6LNKU326KGIJYS3LJSANSN.json","view_paper":"https://pith.science/paper/I5FH6LNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.01249&json=true","fetch_graph":"https://pith.science/api/pith-number/I5FH6LNKU326KGIJYS3LJSANSN/graph.json","fetch_events":"https://pith.science/api/pith-number/I5FH6LNKU326KGIJYS3LJSANSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5FH6LNKU326KGIJYS3LJSANSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5FH6LNKU326KGIJYS3LJSANSN/action/storage_attestation","attest_author":"https://pith.science/pith/I5FH6LNKU326KGIJYS3LJSANSN/action/author_attestation","sign_citation":"https://pith.science/pith/I5FH6LNKU326KGIJYS3LJSANSN/action/citation_signature","submit_replication":"https://pith.science/pith/I5FH6LNKU326KGIJYS3LJSANSN/action/replication_record"}},"created_at":"2026-05-18T00:28:41.397120+00:00","updated_at":"2026-05-18T00:28:41.397120+00:00"}