{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:QHMDL42JKG6SC4M6Z6CWRCSBIS","short_pith_number":"pith:QHMDL42J","schema_version":"1.0","canonical_sha256":"81d835f34951bd21719ecf85688a4144b14983f5faf54e7d98812d67b5a701cc","source":{"kind":"arxiv","id":"1407.4764","version":3},"attestation_state":"computed","paper":{"title":"Efficient On-the-fly Category Retrieval using ConvNets and GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Karen Simonyan, Ken Chatfield","submitted_at":"2014-07-17T18:29:38Z","abstract_excerpt":"We investigate the gains in precision and speed, that can be obtained by using Convolutional Networks (ConvNets) for on-the-fly retrieval - where classifiers are learnt at run time for a textual query from downloaded images, and used to rank large image or video datasets.\n  We make three contributions: (i) we present an evaluation of state-of-the-art image representations for object category retrieval over standard benchmark datasets containing 1M+ images; (ii) we show that ConvNets can be used to obtain features which are incredibly performant, and yet much lower dimensional than previous sta"},"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":"1407.4764","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-07-17T18:29:38Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"22e5b6a2e11d26b767f148ec1f7e366f370f01ca631f49e1c98bf9696cf91e5f","abstract_canon_sha256":"ed123492896bdd3f723b277472822a51ca478862f3032250cc65b67d0c8a3a17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:35:47.128998Z","signature_b64":"AIyilqAMq+4PRSY+2/2txn5AdbaLpuG8BTKQjh4DKUJMA4WrlYPTQ0RmCLJx7ZkKyu/LCgD+pqGFHbYACQm3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81d835f34951bd21719ecf85688a4144b14983f5faf54e7d98812d67b5a701cc","last_reissued_at":"2026-05-18T02:35:47.128618Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:35:47.128618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient On-the-fly Category Retrieval using ConvNets and GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Karen Simonyan, Ken Chatfield","submitted_at":"2014-07-17T18:29:38Z","abstract_excerpt":"We investigate the gains in precision and speed, that can be obtained by using Convolutional Networks (ConvNets) for on-the-fly retrieval - where classifiers are learnt at run time for a textual query from downloaded images, and used to rank large image or video datasets.\n  We make three contributions: (i) we present an evaluation of state-of-the-art image representations for object category retrieval over standard benchmark datasets containing 1M+ images; (ii) we show that ConvNets can be used to obtain features which are incredibly performant, and yet much lower dimensional than previous sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.4764","kind":"arxiv","version":3},"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":"1407.4764","created_at":"2026-05-18T02:35:47.128672+00:00"},{"alias_kind":"arxiv_version","alias_value":"1407.4764v3","created_at":"2026-05-18T02:35:47.128672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.4764","created_at":"2026-05-18T02:35:47.128672+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHMDL42JKG6S","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHMDL42JKG6SC4M6","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHMDL42J","created_at":"2026-05-18T12:28:46.137349+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/QHMDL42JKG6SC4M6Z6CWRCSBIS","json":"https://pith.science/pith/QHMDL42JKG6SC4M6Z6CWRCSBIS.json","graph_json":"https://pith.science/api/pith-number/QHMDL42JKG6SC4M6Z6CWRCSBIS/graph.json","events_json":"https://pith.science/api/pith-number/QHMDL42JKG6SC4M6Z6CWRCSBIS/events.json","paper":"https://pith.science/paper/QHMDL42J"},"agent_actions":{"view_html":"https://pith.science/pith/QHMDL42JKG6SC4M6Z6CWRCSBIS","download_json":"https://pith.science/pith/QHMDL42JKG6SC4M6Z6CWRCSBIS.json","view_paper":"https://pith.science/paper/QHMDL42J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1407.4764&json=true","fetch_graph":"https://pith.science/api/pith-number/QHMDL42JKG6SC4M6Z6CWRCSBIS/graph.json","fetch_events":"https://pith.science/api/pith-number/QHMDL42JKG6SC4M6Z6CWRCSBIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHMDL42JKG6SC4M6Z6CWRCSBIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHMDL42JKG6SC4M6Z6CWRCSBIS/action/storage_attestation","attest_author":"https://pith.science/pith/QHMDL42JKG6SC4M6Z6CWRCSBIS/action/author_attestation","sign_citation":"https://pith.science/pith/QHMDL42JKG6SC4M6Z6CWRCSBIS/action/citation_signature","submit_replication":"https://pith.science/pith/QHMDL42JKG6SC4M6Z6CWRCSBIS/action/replication_record"}},"created_at":"2026-05-18T02:35:47.128672+00:00","updated_at":"2026-05-18T02:35:47.128672+00:00"}