{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QZJUQDAVNOUBPUVGQXVF5TB5SC","short_pith_number":"pith:QZJUQDAV","schema_version":"1.0","canonical_sha256":"8653480c156ba817d2a685ea5ecc3d908123af6955eb00f6b03513234f9d7a2e","source":{"kind":"arxiv","id":"2202.13065","version":2},"attestation_state":"computed","paper":{"title":"An End-to-End Transformer Model for Crowd Localization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Liang, Wei Xu, Xiang Bai","submitted_at":"2022-02-26T05:21:30Z","abstract_excerpt":"Crowd localization, predicting head positions, is a more practical and high-level task than simply counting. Existing methods employ pseudo-bounding boxes or pre-designed localization maps, relying on complex post-processing to obtain the head positions. In this paper, we propose an elegant, end-to-end Crowd Localization Transformer named CLTR that solves the task in the regression-based paradigm. The proposed method views the crowd localization as a direct set prediction problem, taking extracted features and trainable embeddings as input of the transformer-decoder. To reduce the ambiguous po"},"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":"2202.13065","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-26T05:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"a90fedc7701651657dbb0391d9dc649271210aec950d19d5ec2739bb768228fc","abstract_canon_sha256":"24d5e0fe0d6f69956cd3611534ce8b45f82f465458663048459a48ad80c1ed95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:35.249723Z","signature_b64":"nBrQ0AnHu4ZfRbwkCUe2yNvwGfVZ8M92Gkj9Fkx1S4HRrQ2cAh45G6z+pycF0hOQUDz4g0WKy56nABitAlMrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8653480c156ba817d2a685ea5ecc3d908123af6955eb00f6b03513234f9d7a2e","last_reissued_at":"2026-07-05T04:46:35.249308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:35.249308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An End-to-End Transformer Model for Crowd Localization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Liang, Wei Xu, Xiang Bai","submitted_at":"2022-02-26T05:21:30Z","abstract_excerpt":"Crowd localization, predicting head positions, is a more practical and high-level task than simply counting. Existing methods employ pseudo-bounding boxes or pre-designed localization maps, relying on complex post-processing to obtain the head positions. In this paper, we propose an elegant, end-to-end Crowd Localization Transformer named CLTR that solves the task in the regression-based paradigm. The proposed method views the crowd localization as a direct set prediction problem, taking extracted features and trainable embeddings as input of the transformer-decoder. To reduce the ambiguous po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13065","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.13065/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":"2202.13065","created_at":"2026-07-05T04:46:35.249376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13065v2","created_at":"2026-07-05T04:46:35.249376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13065","created_at":"2026-07-05T04:46:35.249376+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZJUQDAVNOUB","created_at":"2026-07-05T04:46:35.249376+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZJUQDAVNOUBPUVG","created_at":"2026-07-05T04:46:35.249376+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZJUQDAV","created_at":"2026-07-05T04:46:35.249376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.06937","citing_title":"Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZJUQDAVNOUBPUVGQXVF5TB5SC","json":"https://pith.science/pith/QZJUQDAVNOUBPUVGQXVF5TB5SC.json","graph_json":"https://pith.science/api/pith-number/QZJUQDAVNOUBPUVGQXVF5TB5SC/graph.json","events_json":"https://pith.science/api/pith-number/QZJUQDAVNOUBPUVGQXVF5TB5SC/events.json","paper":"https://pith.science/paper/QZJUQDAV"},"agent_actions":{"view_html":"https://pith.science/pith/QZJUQDAVNOUBPUVGQXVF5TB5SC","download_json":"https://pith.science/pith/QZJUQDAVNOUBPUVGQXVF5TB5SC.json","view_paper":"https://pith.science/paper/QZJUQDAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13065&json=true","fetch_graph":"https://pith.science/api/pith-number/QZJUQDAVNOUBPUVGQXVF5TB5SC/graph.json","fetch_events":"https://pith.science/api/pith-number/QZJUQDAVNOUBPUVGQXVF5TB5SC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZJUQDAVNOUBPUVGQXVF5TB5SC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZJUQDAVNOUBPUVGQXVF5TB5SC/action/storage_attestation","attest_author":"https://pith.science/pith/QZJUQDAVNOUBPUVGQXVF5TB5SC/action/author_attestation","sign_citation":"https://pith.science/pith/QZJUQDAVNOUBPUVGQXVF5TB5SC/action/citation_signature","submit_replication":"https://pith.science/pith/QZJUQDAVNOUBPUVGQXVF5TB5SC/action/replication_record"}},"created_at":"2026-07-05T04:46:35.249376+00:00","updated_at":"2026-07-05T04:46:35.249376+00:00"}