{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AXVV7V3O6P7ENE5P6GMCIXN76B","short_pith_number":"pith:AXVV7V3O","schema_version":"1.0","canonical_sha256":"05eb5fd76ef3fe4693aff198245dbff05555682d95ff492d2969647a4598847d","source":{"kind":"arxiv","id":"1704.07945","version":2},"attestation_state":"computed","paper":{"title":"Spatio-temporal Person Retrieval via Natural Language Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kuniaki Saito, Masataka Yamaguchi, Tatsuya Harada, Yoshitaka Ushiku","submitted_at":"2017-04-26T02:26:01Z","abstract_excerpt":"In this paper, we address the problem of spatio-temporal person retrieval from multiple videos using a natural language query, in which we output a tube (i.e., a sequence of bounding boxes) which encloses the person described by the query. For this problem, we introduce a novel dataset consisting of videos containing people annotated with bounding boxes for each second and with five natural language descriptions. To retrieve the tube of the person described by a given natural language query, we design a model that combines methods for spatio-temporal human detection and multimodal retrieval. W"},"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":"1704.07945","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-26T02:26:01Z","cross_cats_sorted":[],"title_canon_sha256":"2931440b8bddb34057ea3232ca09a9cf7086ce59171bbf0a45231f34c5b66be2","abstract_canon_sha256":"13dd31b37a3404a96db4e9b773ec029d767fba974c1511b5ce6ea486baa2849e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:52.170929Z","signature_b64":"6SG+Qys7EbOLUGFZQndntKQWB3UYVHLvsX1U4ii3hFr5BKPZIrq/hVNcGYpUFAfX/he5XmDEbsvs0tEXo8vrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05eb5fd76ef3fe4693aff198245dbff05555682d95ff492d2969647a4598847d","last_reissued_at":"2026-05-18T00:36:52.170398Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:52.170398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatio-temporal Person Retrieval via Natural Language Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kuniaki Saito, Masataka Yamaguchi, Tatsuya Harada, Yoshitaka Ushiku","submitted_at":"2017-04-26T02:26:01Z","abstract_excerpt":"In this paper, we address the problem of spatio-temporal person retrieval from multiple videos using a natural language query, in which we output a tube (i.e., a sequence of bounding boxes) which encloses the person described by the query. For this problem, we introduce a novel dataset consisting of videos containing people annotated with bounding boxes for each second and with five natural language descriptions. To retrieve the tube of the person described by a given natural language query, we design a model that combines methods for spatio-temporal human detection and multimodal retrieval. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.07945","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":"1704.07945","created_at":"2026-05-18T00:36:52.170475+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.07945v2","created_at":"2026-05-18T00:36:52.170475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.07945","created_at":"2026-05-18T00:36:52.170475+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXVV7V3O6P7E","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXVV7V3O6P7ENE5P","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXVV7V3O","created_at":"2026-05-18T12:31:08.081275+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/AXVV7V3O6P7ENE5P6GMCIXN76B","json":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B.json","graph_json":"https://pith.science/api/pith-number/AXVV7V3O6P7ENE5P6GMCIXN76B/graph.json","events_json":"https://pith.science/api/pith-number/AXVV7V3O6P7ENE5P6GMCIXN76B/events.json","paper":"https://pith.science/paper/AXVV7V3O"},"agent_actions":{"view_html":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B","download_json":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B.json","view_paper":"https://pith.science/paper/AXVV7V3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.07945&json=true","fetch_graph":"https://pith.science/api/pith-number/AXVV7V3O6P7ENE5P6GMCIXN76B/graph.json","fetch_events":"https://pith.science/api/pith-number/AXVV7V3O6P7ENE5P6GMCIXN76B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/action/storage_attestation","attest_author":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/action/author_attestation","sign_citation":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/action/citation_signature","submit_replication":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/action/replication_record"}},"created_at":"2026-05-18T00:36:52.170475+00:00","updated_at":"2026-05-18T00:36:52.170475+00:00"}