{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AXVV7V3O6P7ENE5P6GMCIXN76B","short_pith_number":"pith:AXVV7V3O","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"},"canonical_sha256":"05eb5fd76ef3fe4693aff198245dbff05555682d95ff492d2969647a4598847d","source":{"kind":"arxiv","id":"1704.07945","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.07945","created_at":"2026-05-18T00:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"1704.07945v2","created_at":"2026-05-18T00:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.07945","created_at":"2026-05-18T00:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"AXVV7V3O6P7E","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"AXVV7V3O6P7ENE5P","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"AXVV7V3O","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AXVV7V3O6P7ENE5P6GMCIXN76B","target":"record","payload":{"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"},"canonical_sha256":"05eb5fd76ef3fe4693aff198245dbff05555682d95ff492d2969647a4598847d","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"},"source_kind":"arxiv","source_id":"1704.07945","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dMI7PS8/fxfw7YTF4RrQc5Alu1b8V0BPyvR/Ub2fBc06B5rsMU34ODraCHmTNsF3VdSPFeL9ex5nIUlT4S/9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T20:32:38.289795Z"},"content_sha256":"cebe77d895142591d5d462aee47ffb23d082613ce6ffd0b3255c71f4f436fa59","schema_version":"1.0","event_id":"sha256:cebe77d895142591d5d462aee47ffb23d082613ce6ffd0b3255c71f4f436fa59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AXVV7V3O6P7ENE5P6GMCIXN76B","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZscIVx8UBynAWrzTA6MMhwXqHdfCa7H0p8DJfO+ats8elmfTRzefKTx0/ov+8dDV/ZeZJgYHOdl3rYX6FfEOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T20:32:38.290146Z"},"content_sha256":"eb9a31fd8638760e6555a48fd173f828b819e943a6f12aaf611e08a1deb903a8","schema_version":"1.0","event_id":"sha256:eb9a31fd8638760e6555a48fd173f828b819e943a6f12aaf611e08a1deb903a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/bundle.json","state_url":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T20:32:38Z","links":{"resolver":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B","bundle":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/bundle.json","state":"https://pith.science/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AXVV7V3O6P7ENE5P6GMCIXN76B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AXVV7V3O6P7ENE5P6GMCIXN76B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"13dd31b37a3404a96db4e9b773ec029d767fba974c1511b5ce6ea486baa2849e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-26T02:26:01Z","title_canon_sha256":"2931440b8bddb34057ea3232ca09a9cf7086ce59171bbf0a45231f34c5b66be2"},"schema_version":"1.0","source":{"id":"1704.07945","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.07945","created_at":"2026-05-18T00:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"1704.07945v2","created_at":"2026-05-18T00:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.07945","created_at":"2026-05-18T00:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"AXVV7V3O6P7E","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"AXVV7V3O6P7ENE5P","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"AXVV7V3O","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:eb9a31fd8638760e6555a48fd173f828b819e943a6f12aaf611e08a1deb903a8","target":"graph","created_at":"2026-05-18T00:36:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Kuniaki Saito, Masataka Yamaguchi, Tatsuya Harada, Yoshitaka Ushiku","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-26T02:26:01Z","title":"Spatio-temporal Person Retrieval via Natural Language Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.07945","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cebe77d895142591d5d462aee47ffb23d082613ce6ffd0b3255c71f4f436fa59","target":"record","created_at":"2026-05-18T00:36:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"13dd31b37a3404a96db4e9b773ec029d767fba974c1511b5ce6ea486baa2849e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-26T02:26:01Z","title_canon_sha256":"2931440b8bddb34057ea3232ca09a9cf7086ce59171bbf0a45231f34c5b66be2"},"schema_version":"1.0","source":{"id":"1704.07945","kind":"arxiv","version":2}},"canonical_sha256":"05eb5fd76ef3fe4693aff198245dbff05555682d95ff492d2969647a4598847d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05eb5fd76ef3fe4693aff198245dbff05555682d95ff492d2969647a4598847d","first_computed_at":"2026-05-18T00:36:52.170398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:52.170398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6SG+Qys7EbOLUGFZQndntKQWB3UYVHLvsX1U4ii3hFr5BKPZIrq/hVNcGYpUFAfX/he5XmDEbsvs0tEXo8vrBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:52.170929Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.07945","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cebe77d895142591d5d462aee47ffb23d082613ce6ffd0b3255c71f4f436fa59","sha256:eb9a31fd8638760e6555a48fd173f828b819e943a6f12aaf611e08a1deb903a8"],"state_sha256":"74e31b6cbb04b0e360a368fe33f91336a3a283a3525b98c017564074c59541e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2DTzQ7YruJnFnU7QhURCdh+3L0J92y0OcuXFQIPwpvtU9K/bu0PIM75xkkgVdeh3WeFPTFkZt9VlZcCKxvdHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T20:32:38.292088Z","bundle_sha256":"0f2879b1c01ae1d71d4116bcb5985d4c261f6c999bbb4fb3caaaf400339077e6"}}