{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YGBNKUGAIV3BVBEIYAJNBAR2YU","short_pith_number":"pith:YGBNKUGA","schema_version":"1.0","canonical_sha256":"c182d550c045761a8488c012d0823ac51982f168d2df095a26df0c50223b7346","source":{"kind":"arxiv","id":"1706.04264","version":2},"attestation_state":"computed","paper":{"title":"von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Milgram, Julien Bohn\\'e, Liming Chen, Md. Abul Hasnat, St\\'ephane Gentric","submitted_at":"2017-06-13T21:43:05Z","abstract_excerpt":"A number of pattern recognition tasks, \\textit{e.g.}, face verification, can be boiled down to classification or clustering of unit length directional feature vectors whose distance can be simply computed by their angle. In this paper, we propose the von Mises-Fisher (vMF) mixture model as the theoretical foundation for an effective deep-learning of such directional features and derive a novel vMF Mixture Loss and its corresponding vMF deep features. The proposed vMF feature learning achieves the characteristics of discriminative learning, \\textit{i.e.}, compacting the instances of the same cl"},"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":"1706.04264","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-13T21:43:05Z","cross_cats_sorted":[],"title_canon_sha256":"f1c968872fdd6c016ebec845639df267cb7bded5bd1c5fcbba63163afb5773bb","abstract_canon_sha256":"7c598b49aaf32c6ef84f2532864b8e3ccf795c935cd6da6783010e6ce6ccb6fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:00.487826Z","signature_b64":"s6ehO/LURz0UPlNkPWwA+yF37lFZ7S+lFdkO/EbrNOO+m5B4xvENzJnpErZw52AbSy/z4pNpE1RA3PZDj86tCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c182d550c045761a8488c012d0823ac51982f168d2df095a26df0c50223b7346","last_reissued_at":"2026-05-18T00:27:00.487117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:00.487117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Milgram, Julien Bohn\\'e, Liming Chen, Md. Abul Hasnat, St\\'ephane Gentric","submitted_at":"2017-06-13T21:43:05Z","abstract_excerpt":"A number of pattern recognition tasks, \\textit{e.g.}, face verification, can be boiled down to classification or clustering of unit length directional feature vectors whose distance can be simply computed by their angle. In this paper, we propose the von Mises-Fisher (vMF) mixture model as the theoretical foundation for an effective deep-learning of such directional features and derive a novel vMF Mixture Loss and its corresponding vMF deep features. The proposed vMF feature learning achieves the characteristics of discriminative learning, \\textit{i.e.}, compacting the instances of the same cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04264","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":""},"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":"1706.04264","created_at":"2026-05-18T00:27:00.487230+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.04264v2","created_at":"2026-05-18T00:27:00.487230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04264","created_at":"2026-05-18T00:27:00.487230+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGBNKUGAIV3B","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGBNKUGAIV3BVBEI","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGBNKUGA","created_at":"2026-05-18T12:31:56.362134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14734","citing_title":"Find the Differences: Differential Morphing Attack Detection vs Face Recognition","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17360","citing_title":"T-DuMpRa: Teacher-guided Dual-path Multi-prototype Retrieval Augmented framework for fine-grained medical image classification","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGBNKUGAIV3BVBEIYAJNBAR2YU","json":"https://pith.science/pith/YGBNKUGAIV3BVBEIYAJNBAR2YU.json","graph_json":"https://pith.science/api/pith-number/YGBNKUGAIV3BVBEIYAJNBAR2YU/graph.json","events_json":"https://pith.science/api/pith-number/YGBNKUGAIV3BVBEIYAJNBAR2YU/events.json","paper":"https://pith.science/paper/YGBNKUGA"},"agent_actions":{"view_html":"https://pith.science/pith/YGBNKUGAIV3BVBEIYAJNBAR2YU","download_json":"https://pith.science/pith/YGBNKUGAIV3BVBEIYAJNBAR2YU.json","view_paper":"https://pith.science/paper/YGBNKUGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.04264&json=true","fetch_graph":"https://pith.science/api/pith-number/YGBNKUGAIV3BVBEIYAJNBAR2YU/graph.json","fetch_events":"https://pith.science/api/pith-number/YGBNKUGAIV3BVBEIYAJNBAR2YU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGBNKUGAIV3BVBEIYAJNBAR2YU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGBNKUGAIV3BVBEIYAJNBAR2YU/action/storage_attestation","attest_author":"https://pith.science/pith/YGBNKUGAIV3BVBEIYAJNBAR2YU/action/author_attestation","sign_citation":"https://pith.science/pith/YGBNKUGAIV3BVBEIYAJNBAR2YU/action/citation_signature","submit_replication":"https://pith.science/pith/YGBNKUGAIV3BVBEIYAJNBAR2YU/action/replication_record"}},"created_at":"2026-05-18T00:27:00.487230+00:00","updated_at":"2026-05-18T00:27:00.487230+00:00"}