{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OVODHZJSUFWAHN2SPR3N2CRI3O","short_pith_number":"pith:OVODHZJS","schema_version":"1.0","canonical_sha256":"755c33e532a16c03b7527c76dd0a28dba96896ec9c0e27a6be211288af546392","source":{"kind":"arxiv","id":"1805.00123","version":1},"attestation_state":"computed","paper":{"title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxun Li, Gang Yu, Jian Sun, Shuai Shao, Tete Xiao, Xiangyu Zhang, Zijian Zhao","submitted_at":"2018-04-30T22:49:54Z","abstract_excerpt":"Human detection has witnessed impressive progress in recent years. However, the occlusion issue of detecting human in highly crowded environments is far from solved. To make matters worse, crowd scenarios are still under-represented in current human detection benchmarks. In this paper, we introduce a new dataset, called CrowdHuman, to better evaluate detectors in crowd scenarios. The CrowdHuman dataset is large, rich-annotated and contains high diversity. There are a total of $470K$ human instances from the train and validation subsets, and $~22.6$ persons per image, with various kinds of occl"},"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":"1805.00123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-30T22:49:54Z","cross_cats_sorted":[],"title_canon_sha256":"a62bc836f96871103ae7c48bac4ce19b3e9c50a6a36871a76f6f944ff96aa56d","abstract_canon_sha256":"4606c4c68ca55a5dc204da43c52cd70950a31088c5f1091b82d834cc8448f8f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:10.501619Z","signature_b64":"WcG3R3hrNcfJaAu5//QIfHML15Q2v/glaRRnpdX4/eK6suz321fiW+LkhuqK4ptHDoWa6EmfjTOpUOf2rbpODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"755c33e532a16c03b7527c76dd0a28dba96896ec9c0e27a6be211288af546392","last_reissued_at":"2026-05-18T00:17:10.500942Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:10.500942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxun Li, Gang Yu, Jian Sun, Shuai Shao, Tete Xiao, Xiangyu Zhang, Zijian Zhao","submitted_at":"2018-04-30T22:49:54Z","abstract_excerpt":"Human detection has witnessed impressive progress in recent years. However, the occlusion issue of detecting human in highly crowded environments is far from solved. To make matters worse, crowd scenarios are still under-represented in current human detection benchmarks. In this paper, we introduce a new dataset, called CrowdHuman, to better evaluate detectors in crowd scenarios. The CrowdHuman dataset is large, rich-annotated and contains high diversity. There are a total of $470K$ human instances from the train and validation subsets, and $~22.6$ persons per image, with various kinds of occl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00123","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":""},"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":"1805.00123","created_at":"2026-05-18T00:17:10.501055+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.00123v1","created_at":"2026-05-18T00:17:10.501055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00123","created_at":"2026-05-18T00:17:10.501055+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVODHZJSUFWA","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVODHZJSUFWAHN2S","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVODHZJS","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2002.09053","citing_title":"Adapted Center and Scale Prediction: More Stable and More Accurate","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2501.15151","citing_title":"SpikeDet: Better Firing Patterns for Accurate and Energy-Efficient Object Detection with Spiking Neural Networks","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2509.02111","citing_title":"NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02773","citing_title":"Generalized Small Object Detection:A Point-Prompted Paradigm and Benchmark","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24036","citing_title":"Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07402","citing_title":"InsHuman: Towards Natural and Identity-Preserving Human Insertion","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14684","citing_title":"DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17439","citing_title":"Attention Is not Everything: Efficient Alternatives for Vision","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVODHZJSUFWAHN2SPR3N2CRI3O","json":"https://pith.science/pith/OVODHZJSUFWAHN2SPR3N2CRI3O.json","graph_json":"https://pith.science/api/pith-number/OVODHZJSUFWAHN2SPR3N2CRI3O/graph.json","events_json":"https://pith.science/api/pith-number/OVODHZJSUFWAHN2SPR3N2CRI3O/events.json","paper":"https://pith.science/paper/OVODHZJS"},"agent_actions":{"view_html":"https://pith.science/pith/OVODHZJSUFWAHN2SPR3N2CRI3O","download_json":"https://pith.science/pith/OVODHZJSUFWAHN2SPR3N2CRI3O.json","view_paper":"https://pith.science/paper/OVODHZJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.00123&json=true","fetch_graph":"https://pith.science/api/pith-number/OVODHZJSUFWAHN2SPR3N2CRI3O/graph.json","fetch_events":"https://pith.science/api/pith-number/OVODHZJSUFWAHN2SPR3N2CRI3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVODHZJSUFWAHN2SPR3N2CRI3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVODHZJSUFWAHN2SPR3N2CRI3O/action/storage_attestation","attest_author":"https://pith.science/pith/OVODHZJSUFWAHN2SPR3N2CRI3O/action/author_attestation","sign_citation":"https://pith.science/pith/OVODHZJSUFWAHN2SPR3N2CRI3O/action/citation_signature","submit_replication":"https://pith.science/pith/OVODHZJSUFWAHN2SPR3N2CRI3O/action/replication_record"}},"created_at":"2026-05-18T00:17:10.501055+00:00","updated_at":"2026-05-18T00:17:10.501055+00:00"}