{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UGMIS52QI62M5ZG73RGKOAWOCN","short_pith_number":"pith:UGMIS52Q","schema_version":"1.0","canonical_sha256":"a19889775047b4cee4dfdc4ca702ce136c08f1ab9595069f2d8f2e0cc14a61b8","source":{"kind":"arxiv","id":"2112.11679","version":2},"attestation_state":"computed","paper":{"title":"Ghost-dil-NetVLAD: A Lightweight Neural Network for Visual Place Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Zhang, Qingyuan Gong, Renhe Liu, Yu Liu","submitted_at":"2021-12-22T06:05:02Z","abstract_excerpt":"Visual place recognition (VPR) is a challenging task with the unbalance between enormous computational cost and high recognition performance. Thanks to the practical feature extraction ability of the lightweight convolution neural networks (CNNs) and the train-ability of the vector of locally aggregated descriptors (VLAD) layer, we propose a lightweight weakly supervised end-to-end neural network consisting of a front-ended perception model called GhostCNN and a learnable VLAD layer as a back-end. GhostCNN is based on Ghost modules that are lightweight CNN-based architectures. They can generat"},"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":"2112.11679","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-22T06:05:02Z","cross_cats_sorted":[],"title_canon_sha256":"5878270d92eb0811b20132130fa587b8746fa545ef19423fd616509001a17994","abstract_canon_sha256":"75c17b43c81cb0b7d557d01a23242fb741924f3beb51746c2185cf21ebe94a69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:37.160068Z","signature_b64":"n4Spo2dRsffaMx1Fx/5oAqfF1hHIitq9vsfY75Vl0p4WTkDcF+LM/4rRUWTfUT9qaBhc332Sd7BWSE0PTtcaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a19889775047b4cee4dfdc4ca702ce136c08f1ab9595069f2d8f2e0cc14a61b8","last_reissued_at":"2026-07-05T08:08:37.159509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:37.159509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ghost-dil-NetVLAD: A Lightweight Neural Network for Visual Place Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Zhang, Qingyuan Gong, Renhe Liu, Yu Liu","submitted_at":"2021-12-22T06:05:02Z","abstract_excerpt":"Visual place recognition (VPR) is a challenging task with the unbalance between enormous computational cost and high recognition performance. Thanks to the practical feature extraction ability of the lightweight convolution neural networks (CNNs) and the train-ability of the vector of locally aggregated descriptors (VLAD) layer, we propose a lightweight weakly supervised end-to-end neural network consisting of a front-ended perception model called GhostCNN and a learnable VLAD layer as a back-end. GhostCNN is based on Ghost modules that are lightweight CNN-based architectures. They can generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11679","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.11679/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":"2112.11679","created_at":"2026-07-05T08:08:37.159566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11679v2","created_at":"2026-07-05T08:08:37.159566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11679","created_at":"2026-07-05T08:08:37.159566+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGMIS52QI62M","created_at":"2026-07-05T08:08:37.159566+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGMIS52QI62M5ZG7","created_at":"2026-07-05T08:08:37.159566+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGMIS52Q","created_at":"2026-07-05T08:08:37.159566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13073","citing_title":"SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGMIS52QI62M5ZG73RGKOAWOCN","json":"https://pith.science/pith/UGMIS52QI62M5ZG73RGKOAWOCN.json","graph_json":"https://pith.science/api/pith-number/UGMIS52QI62M5ZG73RGKOAWOCN/graph.json","events_json":"https://pith.science/api/pith-number/UGMIS52QI62M5ZG73RGKOAWOCN/events.json","paper":"https://pith.science/paper/UGMIS52Q"},"agent_actions":{"view_html":"https://pith.science/pith/UGMIS52QI62M5ZG73RGKOAWOCN","download_json":"https://pith.science/pith/UGMIS52QI62M5ZG73RGKOAWOCN.json","view_paper":"https://pith.science/paper/UGMIS52Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11679&json=true","fetch_graph":"https://pith.science/api/pith-number/UGMIS52QI62M5ZG73RGKOAWOCN/graph.json","fetch_events":"https://pith.science/api/pith-number/UGMIS52QI62M5ZG73RGKOAWOCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGMIS52QI62M5ZG73RGKOAWOCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGMIS52QI62M5ZG73RGKOAWOCN/action/storage_attestation","attest_author":"https://pith.science/pith/UGMIS52QI62M5ZG73RGKOAWOCN/action/author_attestation","sign_citation":"https://pith.science/pith/UGMIS52QI62M5ZG73RGKOAWOCN/action/citation_signature","submit_replication":"https://pith.science/pith/UGMIS52QI62M5ZG73RGKOAWOCN/action/replication_record"}},"created_at":"2026-07-05T08:08:37.159566+00:00","updated_at":"2026-07-05T08:08:37.159566+00:00"}