{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:Q6ZC2YTJVD3PY4K7OW36IEXKCD","short_pith_number":"pith:Q6ZC2YTJ","schema_version":"1.0","canonical_sha256":"87b22d6269a8f6fc715f75b7e412ea10c96fa77b451ccf5583df081dd54d6b45","source":{"kind":"arxiv","id":"1703.08388","version":2},"attestation_state":"computed","paper":{"title":"DeepVisage: Making face recognition simple yet with powerful generalization skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abul Hasnat, Jonathan Milgram, Julien Bohn\\'e, Liming Chen, St\\'ephane Gentric","submitted_at":"2017-03-24T12:41:38Z","abstract_excerpt":"Face recognition (FR) methods report significant performance by adopting the convolutional neural network (CNN) based learning methods. Although CNNs are mostly trained by optimizing the softmax loss, the recent trend shows an improvement of accuracy with different strategies, such as task-specific CNN learning with different loss functions, fine-tuning on target dataset, metric learning and concatenating features from multiple CNNs. Incorporating these tasks obviously requires additional efforts. Moreover, it demotivates the discovery of efficient CNN models for FR which are trained only with"},"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":"1703.08388","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-24T12:41:38Z","cross_cats_sorted":[],"title_canon_sha256":"b9333dac1b07a0a6a658bb5d4bf2caa249a9591c05f2ce95416f58c4fad099f1","abstract_canon_sha256":"19bc6dfd6389e344bebc59bd5a7dfc7fbef4483df4b234bf1f0946c84fa5a4f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:51.229749Z","signature_b64":"JEi0tEz58jmaDO4KAmPcHCDE/Bp0Y/iqaF7m1ApkPuo5cnMl2HW9eLPiEEkDu8F/nqyG2TejW64Mbu4tTFm0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87b22d6269a8f6fc715f75b7e412ea10c96fa77b451ccf5583df081dd54d6b45","last_reissued_at":"2026-05-18T00:46:51.229045Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:51.229045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepVisage: Making face recognition simple yet with powerful generalization skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abul Hasnat, Jonathan Milgram, Julien Bohn\\'e, Liming Chen, St\\'ephane Gentric","submitted_at":"2017-03-24T12:41:38Z","abstract_excerpt":"Face recognition (FR) methods report significant performance by adopting the convolutional neural network (CNN) based learning methods. Although CNNs are mostly trained by optimizing the softmax loss, the recent trend shows an improvement of accuracy with different strategies, such as task-specific CNN learning with different loss functions, fine-tuning on target dataset, metric learning and concatenating features from multiple CNNs. Incorporating these tasks obviously requires additional efforts. Moreover, it demotivates the discovery of efficient CNN models for FR which are trained only with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08388","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":"1703.08388","created_at":"2026-05-18T00:46:51.229169+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.08388v2","created_at":"2026-05-18T00:46:51.229169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08388","created_at":"2026-05-18T00:46:51.229169+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6ZC2YTJVD3P","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6ZC2YTJVD3PY4K7","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6ZC2YTJ","created_at":"2026-05-18T12:31:37.085036+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/Q6ZC2YTJVD3PY4K7OW36IEXKCD","json":"https://pith.science/pith/Q6ZC2YTJVD3PY4K7OW36IEXKCD.json","graph_json":"https://pith.science/api/pith-number/Q6ZC2YTJVD3PY4K7OW36IEXKCD/graph.json","events_json":"https://pith.science/api/pith-number/Q6ZC2YTJVD3PY4K7OW36IEXKCD/events.json","paper":"https://pith.science/paper/Q6ZC2YTJ"},"agent_actions":{"view_html":"https://pith.science/pith/Q6ZC2YTJVD3PY4K7OW36IEXKCD","download_json":"https://pith.science/pith/Q6ZC2YTJVD3PY4K7OW36IEXKCD.json","view_paper":"https://pith.science/paper/Q6ZC2YTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.08388&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6ZC2YTJVD3PY4K7OW36IEXKCD/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6ZC2YTJVD3PY4K7OW36IEXKCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6ZC2YTJVD3PY4K7OW36IEXKCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6ZC2YTJVD3PY4K7OW36IEXKCD/action/storage_attestation","attest_author":"https://pith.science/pith/Q6ZC2YTJVD3PY4K7OW36IEXKCD/action/author_attestation","sign_citation":"https://pith.science/pith/Q6ZC2YTJVD3PY4K7OW36IEXKCD/action/citation_signature","submit_replication":"https://pith.science/pith/Q6ZC2YTJVD3PY4K7OW36IEXKCD/action/replication_record"}},"created_at":"2026-05-18T00:46:51.229169+00:00","updated_at":"2026-05-18T00:46:51.229169+00:00"}