{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7HM7LPDEMJ3Z3OYVZINHEIJNRP","short_pith_number":"pith:7HM7LPDE","schema_version":"1.0","canonical_sha256":"f9d9f5bc6462779dbb15ca1a72212d8bef9efafa8d0343f9590529d6ff3e92fe","source":{"kind":"arxiv","id":"2012.04164","version":3},"attestation_state":"computed","paper":{"title":"Learning Independent Instance Maps for Crowd Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junyu Gao, Qi Wang, Tao Han, Xuelong Li, Yuan Yuan","submitted_at":"2020-12-08T02:17:19Z","abstract_excerpt":"Accurately locating each head's position in the crowd scenes is a crucial task in the field of crowd analysis. However, traditional density-based methods only predict coarse prediction, and segmentation/detection-based methods cannot handle extremely dense scenes and large-range scale-variations crowds. To this end, we propose an end-to-end and straightforward framework for crowd localization, named Independent Instance Map segmentation (IIM). Different from density maps and boxes regression, each instance in IIM is non-overlapped. By segmenting crowds into independent connected components, th"},"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":"2012.04164","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T02:17:19Z","cross_cats_sorted":[],"title_canon_sha256":"97778103857ede58d561dca0370abc9cf0950cf91ca7b1b35a17476cc231b801","abstract_canon_sha256":"53b7e972fc79010464684ab9c0f13bd1f31009c2836c9a0323cb037a154a9362"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:06.888260Z","signature_b64":"FGxGoq7IA5cHDdpwGRT3CxP3WJzjwSCRdOynIh6QDooIGszW3rcOzNVPYieergc6oEPbpJ8DDMVJiWXTUrrgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9d9f5bc6462779dbb15ca1a72212d8bef9efafa8d0343f9590529d6ff3e92fe","last_reissued_at":"2026-07-05T05:06:06.887795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:06.887795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Independent Instance Maps for Crowd Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junyu Gao, Qi Wang, Tao Han, Xuelong Li, Yuan Yuan","submitted_at":"2020-12-08T02:17:19Z","abstract_excerpt":"Accurately locating each head's position in the crowd scenes is a crucial task in the field of crowd analysis. However, traditional density-based methods only predict coarse prediction, and segmentation/detection-based methods cannot handle extremely dense scenes and large-range scale-variations crowds. To this end, we propose an end-to-end and straightforward framework for crowd localization, named Independent Instance Map segmentation (IIM). Different from density maps and boxes regression, each instance in IIM is non-overlapped. By segmenting crowds into independent connected components, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04164","kind":"arxiv","version":3},"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/2012.04164/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":"2012.04164","created_at":"2026-07-05T05:06:06.887861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.04164v3","created_at":"2026-07-05T05:06:06.887861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04164","created_at":"2026-07-05T05:06:06.887861+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HM7LPDEMJ3Z","created_at":"2026-07-05T05:06:06.887861+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HM7LPDEMJ3Z3OYV","created_at":"2026-07-05T05:06:06.887861+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HM7LPDE","created_at":"2026-07-05T05:06:06.887861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21943","citing_title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7HM7LPDEMJ3Z3OYVZINHEIJNRP","json":"https://pith.science/pith/7HM7LPDEMJ3Z3OYVZINHEIJNRP.json","graph_json":"https://pith.science/api/pith-number/7HM7LPDEMJ3Z3OYVZINHEIJNRP/graph.json","events_json":"https://pith.science/api/pith-number/7HM7LPDEMJ3Z3OYVZINHEIJNRP/events.json","paper":"https://pith.science/paper/7HM7LPDE"},"agent_actions":{"view_html":"https://pith.science/pith/7HM7LPDEMJ3Z3OYVZINHEIJNRP","download_json":"https://pith.science/pith/7HM7LPDEMJ3Z3OYVZINHEIJNRP.json","view_paper":"https://pith.science/paper/7HM7LPDE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.04164&json=true","fetch_graph":"https://pith.science/api/pith-number/7HM7LPDEMJ3Z3OYVZINHEIJNRP/graph.json","fetch_events":"https://pith.science/api/pith-number/7HM7LPDEMJ3Z3OYVZINHEIJNRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HM7LPDEMJ3Z3OYVZINHEIJNRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HM7LPDEMJ3Z3OYVZINHEIJNRP/action/storage_attestation","attest_author":"https://pith.science/pith/7HM7LPDEMJ3Z3OYVZINHEIJNRP/action/author_attestation","sign_citation":"https://pith.science/pith/7HM7LPDEMJ3Z3OYVZINHEIJNRP/action/citation_signature","submit_replication":"https://pith.science/pith/7HM7LPDEMJ3Z3OYVZINHEIJNRP/action/replication_record"}},"created_at":"2026-07-05T05:06:06.887861+00:00","updated_at":"2026-07-05T05:06:06.887861+00:00"}