{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LZ4OBX2FLLPSIMLPLKMG7JRSSI","short_pith_number":"pith:LZ4OBX2F","schema_version":"1.0","canonical_sha256":"5e78e0df455adf24316f5a986fa63292046fefc28460a18a382ae0b0a9c0a27c","source":{"kind":"arxiv","id":"1806.00974","version":2},"attestation_state":"computed","paper":{"title":"ALMN: Deep Embedding Learning with Geometrical Virtual Point Generating","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghui Chen, Weihong Deng","submitted_at":"2018-06-04T06:38:28Z","abstract_excerpt":"Deep embedding learning becomes more attractive for discriminative feature learning, but many methods still require hard-class mining, which is computationally complex and performance-sensitive. To this end, we propose Adaptive Large Margin N-Pair loss (ALMN) to address the aforementioned issues. Instead of exploring hard example-mining strategy, we introduce the concept of large margin constraint. This constraint aims at encouraging local-adaptive large angular decision margin among dissimilar samples in multimodal feature space so as to significantly encourage intraclass compactness and inte"},"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":"1806.00974","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-04T06:38:28Z","cross_cats_sorted":[],"title_canon_sha256":"a8138b1b1815ef3922e08de7905ddb3d1967093f3824449c5ed75389c6819e31","abstract_canon_sha256":"aa417c6f0202f320a39de409ddbf6e905b4c04073b193efe3f7eb254ee5ecd31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:13.318307Z","signature_b64":"BdIskeFOS9kXAfsU3suXD3xKUJNBiSJ+s75xAOcbeFUqBr76LYiw+Wgoaqv9GICZ9nJDoGeuLy6nW3LtIfHrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e78e0df455adf24316f5a986fa63292046fefc28460a18a382ae0b0a9c0a27c","last_reissued_at":"2026-05-18T00:14:13.317766Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:13.317766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALMN: Deep Embedding Learning with Geometrical Virtual Point Generating","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghui Chen, Weihong Deng","submitted_at":"2018-06-04T06:38:28Z","abstract_excerpt":"Deep embedding learning becomes more attractive for discriminative feature learning, but many methods still require hard-class mining, which is computationally complex and performance-sensitive. To this end, we propose Adaptive Large Margin N-Pair loss (ALMN) to address the aforementioned issues. Instead of exploring hard example-mining strategy, we introduce the concept of large margin constraint. This constraint aims at encouraging local-adaptive large angular decision margin among dissimilar samples in multimodal feature space so as to significantly encourage intraclass compactness and inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00974","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":"1806.00974","created_at":"2026-05-18T00:14:13.317847+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.00974v2","created_at":"2026-05-18T00:14:13.317847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00974","created_at":"2026-05-18T00:14:13.317847+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZ4OBX2FLLPS","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZ4OBX2FLLPSIMLP","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZ4OBX2F","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.11832","citing_title":"Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZ4OBX2FLLPSIMLPLKMG7JRSSI","json":"https://pith.science/pith/LZ4OBX2FLLPSIMLPLKMG7JRSSI.json","graph_json":"https://pith.science/api/pith-number/LZ4OBX2FLLPSIMLPLKMG7JRSSI/graph.json","events_json":"https://pith.science/api/pith-number/LZ4OBX2FLLPSIMLPLKMG7JRSSI/events.json","paper":"https://pith.science/paper/LZ4OBX2F"},"agent_actions":{"view_html":"https://pith.science/pith/LZ4OBX2FLLPSIMLPLKMG7JRSSI","download_json":"https://pith.science/pith/LZ4OBX2FLLPSIMLPLKMG7JRSSI.json","view_paper":"https://pith.science/paper/LZ4OBX2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.00974&json=true","fetch_graph":"https://pith.science/api/pith-number/LZ4OBX2FLLPSIMLPLKMG7JRSSI/graph.json","fetch_events":"https://pith.science/api/pith-number/LZ4OBX2FLLPSIMLPLKMG7JRSSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZ4OBX2FLLPSIMLPLKMG7JRSSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZ4OBX2FLLPSIMLPLKMG7JRSSI/action/storage_attestation","attest_author":"https://pith.science/pith/LZ4OBX2FLLPSIMLPLKMG7JRSSI/action/author_attestation","sign_citation":"https://pith.science/pith/LZ4OBX2FLLPSIMLPLKMG7JRSSI/action/citation_signature","submit_replication":"https://pith.science/pith/LZ4OBX2FLLPSIMLPLKMG7JRSSI/action/replication_record"}},"created_at":"2026-05-18T00:14:13.317847+00:00","updated_at":"2026-05-18T00:14:13.317847+00:00"}