{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:V2MA7NSF3GXJWOSTL7CBDB7VOA","short_pith_number":"pith:V2MA7NSF","schema_version":"1.0","canonical_sha256":"ae980fb645d9ae9b3a535fc41187f57038474a8a7a54d8bd4ee6bc769698ad86","source":{"kind":"arxiv","id":"2006.03254","version":1},"attestation_state":"computed","paper":{"title":"TCDesc: Learning Topology Consistent Descriptors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanyang Meng, Honghu Pan, Wei Liu, Yongsheng Liang, Zhenyu He","submitted_at":"2020-06-05T06:46:30Z","abstract_excerpt":"Triplet loss is widely used for learning local descriptors from image patch. However, triplet loss only minimizes the Euclidean distance between matching descriptors and maximizes that between the non-matching descriptors, which neglects the topology similarity between two descriptor sets. In this paper, we propose topology measure besides Euclidean distance to learn topology consistent descriptors by considering kNN descriptors of positive sample. First we establish a novel topology vector for each descriptor followed by Locally Linear Embedding (LLE) to indicate the topological relation amon"},"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":"2006.03254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-05T06:46:30Z","cross_cats_sorted":[],"title_canon_sha256":"1dddaf05d785c20e9e68aefecac90284ef7419c2945b73093ce86ef468a274aa","abstract_canon_sha256":"164b57e75d40b4e10e5648d1cbcba5b35f5ae39d56099bcdb72248518daca263"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:16.415706Z","signature_b64":"wBDfBvsZKle1iQDGRRwzgrqbtkdVsBsvNOh9Nbrqcl37qUP+Eig3Zmn+qhi+3kSpXF6GxBmF+JSMecjYNYdPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae980fb645d9ae9b3a535fc41187f57038474a8a7a54d8bd4ee6bc769698ad86","last_reissued_at":"2026-07-05T01:08:16.415343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:16.415343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TCDesc: Learning Topology Consistent Descriptors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanyang Meng, Honghu Pan, Wei Liu, Yongsheng Liang, Zhenyu He","submitted_at":"2020-06-05T06:46:30Z","abstract_excerpt":"Triplet loss is widely used for learning local descriptors from image patch. However, triplet loss only minimizes the Euclidean distance between matching descriptors and maximizes that between the non-matching descriptors, which neglects the topology similarity between two descriptor sets. In this paper, we propose topology measure besides Euclidean distance to learn topology consistent descriptors by considering kNN descriptors of positive sample. First we establish a novel topology vector for each descriptor followed by Locally Linear Embedding (LLE) to indicate the topological relation amon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03254","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/2006.03254/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":"2006.03254","created_at":"2026-07-05T01:08:16.415402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.03254v1","created_at":"2026-07-05T01:08:16.415402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03254","created_at":"2026-07-05T01:08:16.415402+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2MA7NSF3GXJ","created_at":"2026-07-05T01:08:16.415402+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2MA7NSF3GXJWOST","created_at":"2026-07-05T01:08:16.415402+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2MA7NSF","created_at":"2026-07-05T01:08:16.415402+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/V2MA7NSF3GXJWOSTL7CBDB7VOA","json":"https://pith.science/pith/V2MA7NSF3GXJWOSTL7CBDB7VOA.json","graph_json":"https://pith.science/api/pith-number/V2MA7NSF3GXJWOSTL7CBDB7VOA/graph.json","events_json":"https://pith.science/api/pith-number/V2MA7NSF3GXJWOSTL7CBDB7VOA/events.json","paper":"https://pith.science/paper/V2MA7NSF"},"agent_actions":{"view_html":"https://pith.science/pith/V2MA7NSF3GXJWOSTL7CBDB7VOA","download_json":"https://pith.science/pith/V2MA7NSF3GXJWOSTL7CBDB7VOA.json","view_paper":"https://pith.science/paper/V2MA7NSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.03254&json=true","fetch_graph":"https://pith.science/api/pith-number/V2MA7NSF3GXJWOSTL7CBDB7VOA/graph.json","fetch_events":"https://pith.science/api/pith-number/V2MA7NSF3GXJWOSTL7CBDB7VOA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2MA7NSF3GXJWOSTL7CBDB7VOA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2MA7NSF3GXJWOSTL7CBDB7VOA/action/storage_attestation","attest_author":"https://pith.science/pith/V2MA7NSF3GXJWOSTL7CBDB7VOA/action/author_attestation","sign_citation":"https://pith.science/pith/V2MA7NSF3GXJWOSTL7CBDB7VOA/action/citation_signature","submit_replication":"https://pith.science/pith/V2MA7NSF3GXJWOSTL7CBDB7VOA/action/replication_record"}},"created_at":"2026-07-05T01:08:16.415402+00:00","updated_at":"2026-07-05T01:08:16.415402+00:00"}