{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6TPREI2DMNRQZXPRD3MO7VUZZC","short_pith_number":"pith:6TPREI2D","schema_version":"1.0","canonical_sha256":"f4df12234363630cddf11ed8efd699c8b9506e4cfc48ecdc02db897744b166f6","source":{"kind":"arxiv","id":"2206.08172","version":1},"attestation_state":"computed","paper":{"title":"RefCrowd: Grounding the Target in Crowd with Referring Expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanman Meng, Heqian Qiu, Hongliang Li, Lanxiao Wang, Qingbo Wu, Taijin Zhao","submitted_at":"2022-06-16T13:39:26Z","abstract_excerpt":"Crowd understanding has aroused the widespread interest in vision domain due to its important practical significance. Unfortunately, there is no effort to explore crowd understanding in multi-modal domain that bridges natural language and computer vision. Referring expression comprehension (REF) is such a representative multi-modal task. Current REF studies focus more on grounding the target object from multiple distinctive categories in general scenarios. It is difficult to applied to complex real-world crowd understanding. To fill this gap, we propose a new challenging dataset, called RefCro"},"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":"2206.08172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T13:39:26Z","cross_cats_sorted":[],"title_canon_sha256":"3cd61220257ba5e28c863b9e30bc67857bdfc16157caf3f90eef0074d14ce66f","abstract_canon_sha256":"d3f2e4a9df4745136fd63e897453704b3ec3b49a28253d3b7de93fd1d27e7cd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:22.751226Z","signature_b64":"C0Nujf19wldYfNsOSygxDZH+/JmgztriAx+fiwV5XvRShFCN7W69vY64TYg3DBwV3blSJkERFf80WNDtcy7uAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4df12234363630cddf11ed8efd699c8b9506e4cfc48ecdc02db897744b166f6","last_reissued_at":"2026-07-05T04:32:22.750795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:22.750795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RefCrowd: Grounding the Target in Crowd with Referring Expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanman Meng, Heqian Qiu, Hongliang Li, Lanxiao Wang, Qingbo Wu, Taijin Zhao","submitted_at":"2022-06-16T13:39:26Z","abstract_excerpt":"Crowd understanding has aroused the widespread interest in vision domain due to its important practical significance. Unfortunately, there is no effort to explore crowd understanding in multi-modal domain that bridges natural language and computer vision. Referring expression comprehension (REF) is such a representative multi-modal task. Current REF studies focus more on grounding the target object from multiple distinctive categories in general scenarios. It is difficult to applied to complex real-world crowd understanding. To fill this gap, we propose a new challenging dataset, called RefCro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08172","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/2206.08172/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":"2206.08172","created_at":"2026-07-05T04:32:22.750853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08172v1","created_at":"2026-07-05T04:32:22.750853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08172","created_at":"2026-07-05T04:32:22.750853+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TPREI2DMNRQ","created_at":"2026-07-05T04:32:22.750853+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TPREI2DMNRQZXPR","created_at":"2026-07-05T04:32:22.750853+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TPREI2D","created_at":"2026-07-05T04:32:22.750853+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/6TPREI2DMNRQZXPRD3MO7VUZZC","json":"https://pith.science/pith/6TPREI2DMNRQZXPRD3MO7VUZZC.json","graph_json":"https://pith.science/api/pith-number/6TPREI2DMNRQZXPRD3MO7VUZZC/graph.json","events_json":"https://pith.science/api/pith-number/6TPREI2DMNRQZXPRD3MO7VUZZC/events.json","paper":"https://pith.science/paper/6TPREI2D"},"agent_actions":{"view_html":"https://pith.science/pith/6TPREI2DMNRQZXPRD3MO7VUZZC","download_json":"https://pith.science/pith/6TPREI2DMNRQZXPRD3MO7VUZZC.json","view_paper":"https://pith.science/paper/6TPREI2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08172&json=true","fetch_graph":"https://pith.science/api/pith-number/6TPREI2DMNRQZXPRD3MO7VUZZC/graph.json","fetch_events":"https://pith.science/api/pith-number/6TPREI2DMNRQZXPRD3MO7VUZZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TPREI2DMNRQZXPRD3MO7VUZZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TPREI2DMNRQZXPRD3MO7VUZZC/action/storage_attestation","attest_author":"https://pith.science/pith/6TPREI2DMNRQZXPRD3MO7VUZZC/action/author_attestation","sign_citation":"https://pith.science/pith/6TPREI2DMNRQZXPRD3MO7VUZZC/action/citation_signature","submit_replication":"https://pith.science/pith/6TPREI2DMNRQZXPRD3MO7VUZZC/action/replication_record"}},"created_at":"2026-07-05T04:32:22.750853+00:00","updated_at":"2026-07-05T04:32:22.750853+00:00"}