{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UVGPMEYKDGFFITRXJR75PYWZQ2","short_pith_number":"pith:UVGPMEYK","schema_version":"1.0","canonical_sha256":"a54cf6130a198a544e374c7fd7e2d98684cd61201b7f6762a068bcc7a0fb445b","source":{"kind":"arxiv","id":"1911.03826","version":1},"attestation_state":"computed","paper":{"title":"Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuwen Tan, Hui Wu, Paola Cascante-Bonilla, Song Feng, Vicente Ordonez, Xiaoxiao Guo","submitted_at":"2019-11-10T01:50:16Z","abstract_excerpt":"This paper explores the task of interactive image retrieval using natural language queries, where a user progressively provides input queries to refine a set of retrieval results. Moreover, our work explores this problem in the context of complex image scenes containing multiple objects. We propose Drill-down, an effective framework for encoding multiple queries with an efficient compact state representation that significantly extends current methods for single-round image retrieval. We show that using multiple rounds of natural language queries as input can be surprisingly effective to find a"},"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":"1911.03826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-11-10T01:50:16Z","cross_cats_sorted":[],"title_canon_sha256":"28dc2e954c471cf8db7f2130a0b9ccb8920a99bdbf6b1bd86d8b9b6a33959b90","abstract_canon_sha256":"5177a6201ca0a70a4ea32374efdb137816f4c93fb9a093265269cf0337164833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:16.320495Z","signature_b64":"Dp+iuPN6nLrDH8qlbqh+lssFpOt0MJovA35KN/LVDF43nvuGFAEXO1iBS9kuXT7DOYLt1IKxj1OOJnrF2tLsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a54cf6130a198a544e374c7fd7e2d98684cd61201b7f6762a068bcc7a0fb445b","last_reissued_at":"2026-07-05T00:18:16.320071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:16.320071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuwen Tan, Hui Wu, Paola Cascante-Bonilla, Song Feng, Vicente Ordonez, Xiaoxiao Guo","submitted_at":"2019-11-10T01:50:16Z","abstract_excerpt":"This paper explores the task of interactive image retrieval using natural language queries, where a user progressively provides input queries to refine a set of retrieval results. Moreover, our work explores this problem in the context of complex image scenes containing multiple objects. We propose Drill-down, an effective framework for encoding multiple queries with an efficient compact state representation that significantly extends current methods for single-round image retrieval. We show that using multiple rounds of natural language queries as input can be surprisingly effective to find a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03826","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/1911.03826/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":"1911.03826","created_at":"2026-07-05T00:18:16.320129+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.03826v1","created_at":"2026-07-05T00:18:16.320129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03826","created_at":"2026-07-05T00:18:16.320129+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVGPMEYKDGFF","created_at":"2026-07-05T00:18:16.320129+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVGPMEYKDGFFITRX","created_at":"2026-07-05T00:18:16.320129+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVGPMEYK","created_at":"2026-07-05T00:18:16.320129+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/UVGPMEYKDGFFITRXJR75PYWZQ2","json":"https://pith.science/pith/UVGPMEYKDGFFITRXJR75PYWZQ2.json","graph_json":"https://pith.science/api/pith-number/UVGPMEYKDGFFITRXJR75PYWZQ2/graph.json","events_json":"https://pith.science/api/pith-number/UVGPMEYKDGFFITRXJR75PYWZQ2/events.json","paper":"https://pith.science/paper/UVGPMEYK"},"agent_actions":{"view_html":"https://pith.science/pith/UVGPMEYKDGFFITRXJR75PYWZQ2","download_json":"https://pith.science/pith/UVGPMEYKDGFFITRXJR75PYWZQ2.json","view_paper":"https://pith.science/paper/UVGPMEYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.03826&json=true","fetch_graph":"https://pith.science/api/pith-number/UVGPMEYKDGFFITRXJR75PYWZQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/UVGPMEYKDGFFITRXJR75PYWZQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVGPMEYKDGFFITRXJR75PYWZQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVGPMEYKDGFFITRXJR75PYWZQ2/action/storage_attestation","attest_author":"https://pith.science/pith/UVGPMEYKDGFFITRXJR75PYWZQ2/action/author_attestation","sign_citation":"https://pith.science/pith/UVGPMEYKDGFFITRXJR75PYWZQ2/action/citation_signature","submit_replication":"https://pith.science/pith/UVGPMEYKDGFFITRXJR75PYWZQ2/action/replication_record"}},"created_at":"2026-07-05T00:18:16.320129+00:00","updated_at":"2026-07-05T00:18:16.320129+00:00"}