{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NRIQ6ESXDBBNRMPIERX5BYM5QL","short_pith_number":"pith:NRIQ6ESX","schema_version":"1.0","canonical_sha256":"6c510f12571842d8b1e8246fd0e19d82f42b2036019638a81776d062c4a95dfd","source":{"kind":"arxiv","id":"1711.09509","version":2},"attestation_state":"computed","paper":{"title":"Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ryota Hinami, Shin'ichi Satoh","submitted_at":"2017-11-27T02:25:34Z","abstract_excerpt":"Thanks to the success of object detection technology, we can retrieve objects of the specified classes even from huge image collections. However, the current state-of-the-art object detectors (such as Faster R-CNN) can only handle pre-specified classes. In addition, large amounts of positive and negative visual samples are required for training. In this paper, we address the problem of open-vocabulary object retrieval and localization, where the target object is specified by a textual query (e.g., a word or phrase). We first propose Query-Adaptive R-CNN, a simple extension of Faster R-CNN adap"},"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":"1711.09509","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-27T02:25:34Z","cross_cats_sorted":[],"title_canon_sha256":"9da1fa0c9debadb7f50caaa79417d8ebd4081eeb64f4ecf219948f810cafc52c","abstract_canon_sha256":"c877249e2af9a02a72b2a0b2d08c198bcb4981c197bd57d48ff8afbbbc057500"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:41.106435Z","signature_b64":"DazEpLH4uwtX+icq4jTvDblhBus1p84RZf5ElUxXhjd7PAvt/qB9G5LmOQ9OZOat7Ce0L2O4Ed6GBDoal/8mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c510f12571842d8b1e8246fd0e19d82f42b2036019638a81776d062c4a95dfd","last_reissued_at":"2026-05-18T00:06:41.105869Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:41.105869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ryota Hinami, Shin'ichi Satoh","submitted_at":"2017-11-27T02:25:34Z","abstract_excerpt":"Thanks to the success of object detection technology, we can retrieve objects of the specified classes even from huge image collections. However, the current state-of-the-art object detectors (such as Faster R-CNN) can only handle pre-specified classes. In addition, large amounts of positive and negative visual samples are required for training. In this paper, we address the problem of open-vocabulary object retrieval and localization, where the target object is specified by a textual query (e.g., a word or phrase). We first propose Query-Adaptive R-CNN, a simple extension of Faster R-CNN adap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09509","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":"1711.09509","created_at":"2026-05-18T00:06:41.105951+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.09509v2","created_at":"2026-05-18T00:06:41.105951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09509","created_at":"2026-05-18T00:06:41.105951+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRIQ6ESXDBBN","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRIQ6ESXDBBNRMPI","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRIQ6ESX","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.03557","citing_title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NRIQ6ESXDBBNRMPIERX5BYM5QL","json":"https://pith.science/pith/NRIQ6ESXDBBNRMPIERX5BYM5QL.json","graph_json":"https://pith.science/api/pith-number/NRIQ6ESXDBBNRMPIERX5BYM5QL/graph.json","events_json":"https://pith.science/api/pith-number/NRIQ6ESXDBBNRMPIERX5BYM5QL/events.json","paper":"https://pith.science/paper/NRIQ6ESX"},"agent_actions":{"view_html":"https://pith.science/pith/NRIQ6ESXDBBNRMPIERX5BYM5QL","download_json":"https://pith.science/pith/NRIQ6ESXDBBNRMPIERX5BYM5QL.json","view_paper":"https://pith.science/paper/NRIQ6ESX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.09509&json=true","fetch_graph":"https://pith.science/api/pith-number/NRIQ6ESXDBBNRMPIERX5BYM5QL/graph.json","fetch_events":"https://pith.science/api/pith-number/NRIQ6ESXDBBNRMPIERX5BYM5QL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRIQ6ESXDBBNRMPIERX5BYM5QL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRIQ6ESXDBBNRMPIERX5BYM5QL/action/storage_attestation","attest_author":"https://pith.science/pith/NRIQ6ESXDBBNRMPIERX5BYM5QL/action/author_attestation","sign_citation":"https://pith.science/pith/NRIQ6ESXDBBNRMPIERX5BYM5QL/action/citation_signature","submit_replication":"https://pith.science/pith/NRIQ6ESXDBBNRMPIERX5BYM5QL/action/replication_record"}},"created_at":"2026-05-18T00:06:41.105951+00:00","updated_at":"2026-05-18T00:06:41.105951+00:00"}