{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UD7UVCJT4ALWK4NM27EOIJ2PO7","short_pith_number":"pith:UD7UVCJT","schema_version":"1.0","canonical_sha256":"a0ff4a8933e0176571acd7c8e4274f77fe8716a7136dd40348f33b4753c26de5","source":{"kind":"arxiv","id":"1909.00632","version":1},"attestation_state":"computed","paper":{"title":"Towards Flops-constrained Face Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglu Song, Jihao Liu, Junjie Yan, Manyuan Zhang, Yucong Zhou, Yu Liu","submitted_at":"2019-09-02T09:42:52Z","abstract_excerpt":"Large scale face recognition is challenging especially when the computational budget is limited. Given a \\textit{flops} upper bound, the key is to find the optimal neural network architecture and optimization method. In this article, we briefly introduce the solutions of team 'trojans' for the ICCV19 - Lightweight Face Recognition Challenge~\\cite{lfr}. The challenge requires each submission to be one single model with the computational budget no higher than 30 GFlops. We introduce a searched network architecture `Efficient PolyFace' based on the Flops constraint, a novel loss function `ArcNegF"},"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":"1909.00632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-02T09:42:52Z","cross_cats_sorted":[],"title_canon_sha256":"b45f95bbdce59e8399a5e508ecf82647eb5f483713d0587755da46c4bab97a6a","abstract_canon_sha256":"d34df8e3b564c3290e98f808f6bb027b754671bc616e2378e7316f091a2a009f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:11.611281Z","signature_b64":"hvUu/kq6xtvVFzC4s8G+ci5QyxOPsEU8VARaSgyh1pgnW7OM19GlTJurDuZ7vT5IsB76gZQH08EeXA4hlA8OCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0ff4a8933e0176571acd7c8e4274f77fe8716a7136dd40348f33b4753c26de5","last_reissued_at":"2026-07-05T00:01:11.610797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:11.610797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Flops-constrained Face Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglu Song, Jihao Liu, Junjie Yan, Manyuan Zhang, Yucong Zhou, Yu Liu","submitted_at":"2019-09-02T09:42:52Z","abstract_excerpt":"Large scale face recognition is challenging especially when the computational budget is limited. Given a \\textit{flops} upper bound, the key is to find the optimal neural network architecture and optimization method. In this article, we briefly introduce the solutions of team 'trojans' for the ICCV19 - Lightweight Face Recognition Challenge~\\cite{lfr}. The challenge requires each submission to be one single model with the computational budget no higher than 30 GFlops. We introduce a searched network architecture `Efficient PolyFace' based on the Flops constraint, a novel loss function `ArcNegF"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00632","kind":"arxiv","version":1},"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/1909.00632/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":"1909.00632","created_at":"2026-07-05T00:01:11.610862+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00632v1","created_at":"2026-07-05T00:01:11.610862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00632","created_at":"2026-07-05T00:01:11.610862+00:00"},{"alias_kind":"pith_short_12","alias_value":"UD7UVCJT4ALW","created_at":"2026-07-05T00:01:11.610862+00:00"},{"alias_kind":"pith_short_16","alias_value":"UD7UVCJT4ALWK4NM","created_at":"2026-07-05T00:01:11.610862+00:00"},{"alias_kind":"pith_short_8","alias_value":"UD7UVCJT","created_at":"2026-07-05T00:01:11.610862+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/UD7UVCJT4ALWK4NM27EOIJ2PO7","json":"https://pith.science/pith/UD7UVCJT4ALWK4NM27EOIJ2PO7.json","graph_json":"https://pith.science/api/pith-number/UD7UVCJT4ALWK4NM27EOIJ2PO7/graph.json","events_json":"https://pith.science/api/pith-number/UD7UVCJT4ALWK4NM27EOIJ2PO7/events.json","paper":"https://pith.science/paper/UD7UVCJT"},"agent_actions":{"view_html":"https://pith.science/pith/UD7UVCJT4ALWK4NM27EOIJ2PO7","download_json":"https://pith.science/pith/UD7UVCJT4ALWK4NM27EOIJ2PO7.json","view_paper":"https://pith.science/paper/UD7UVCJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00632&json=true","fetch_graph":"https://pith.science/api/pith-number/UD7UVCJT4ALWK4NM27EOIJ2PO7/graph.json","fetch_events":"https://pith.science/api/pith-number/UD7UVCJT4ALWK4NM27EOIJ2PO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UD7UVCJT4ALWK4NM27EOIJ2PO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UD7UVCJT4ALWK4NM27EOIJ2PO7/action/storage_attestation","attest_author":"https://pith.science/pith/UD7UVCJT4ALWK4NM27EOIJ2PO7/action/author_attestation","sign_citation":"https://pith.science/pith/UD7UVCJT4ALWK4NM27EOIJ2PO7/action/citation_signature","submit_replication":"https://pith.science/pith/UD7UVCJT4ALWK4NM27EOIJ2PO7/action/replication_record"}},"created_at":"2026-07-05T00:01:11.610862+00:00","updated_at":"2026-07-05T00:01:11.610862+00:00"}