{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:U37NGQWX6V2MP7IGW4WX4J3IVZ","short_pith_number":"pith:U37NGQWX","schema_version":"1.0","canonical_sha256":"a6fed342d7f574c7fd06b72d7e2768ae699fed12bd1c58c9b9c9a0a80bf6ea23","source":{"kind":"arxiv","id":"2206.08084","version":1},"attestation_state":"computed","paper":{"title":"An Improved Normed-Deformable Convolution for Crowd Counting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Qin, Wangmeng Zuo, Weigang Lu, Xin Zhong, Zhaoyi Yan","submitted_at":"2022-06-16T10:56:26Z","abstract_excerpt":"In recent years, crowd counting has become an important issue in computer vision. In most methods, the density maps are generated by convolving with a Gaussian kernel from the ground-truth dot maps which are marked around the center of human heads. Due to the fixed geometric structures in CNNs and indistinct head-scale information, the head features are obtained incompletely. Deformable convolution is proposed to exploit the scale-adaptive capabilities for CNN features in the heads. By learning the coordinate offsets of the sampling points, it is tractable to improve the ability to adjust the "},"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":"2206.08084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T10:56:26Z","cross_cats_sorted":[],"title_canon_sha256":"7ce39a35cb5bf2ce4e54f8f7394140487757636dafa6041b0b139a3bbc78cd61","abstract_canon_sha256":"216fd1abae94a23cbd1afae61ac38e6daf503236f878d0467dd3a1f4c9842886"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:01.223639Z","signature_b64":"rNqF8EYGL4jm6rM9LR0AGN92WrHspdFOyCWu82gpIMwNmvge3Vo1MGmkbSK56EpR6S/B7SoPCLmf+rtGhJIhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6fed342d7f574c7fd06b72d7e2768ae699fed12bd1c58c9b9c9a0a80bf6ea23","last_reissued_at":"2026-07-05T04:55:01.223162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:01.223162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Improved Normed-Deformable Convolution for Crowd Counting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Qin, Wangmeng Zuo, Weigang Lu, Xin Zhong, Zhaoyi Yan","submitted_at":"2022-06-16T10:56:26Z","abstract_excerpt":"In recent years, crowd counting has become an important issue in computer vision. In most methods, the density maps are generated by convolving with a Gaussian kernel from the ground-truth dot maps which are marked around the center of human heads. Due to the fixed geometric structures in CNNs and indistinct head-scale information, the head features are obtained incompletely. Deformable convolution is proposed to exploit the scale-adaptive capabilities for CNN features in the heads. By learning the coordinate offsets of the sampling points, it is tractable to improve the ability to adjust the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08084","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/2206.08084/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":"2206.08084","created_at":"2026-07-05T04:55:01.223217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08084v1","created_at":"2026-07-05T04:55:01.223217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08084","created_at":"2026-07-05T04:55:01.223217+00:00"},{"alias_kind":"pith_short_12","alias_value":"U37NGQWX6V2M","created_at":"2026-07-05T04:55:01.223217+00:00"},{"alias_kind":"pith_short_16","alias_value":"U37NGQWX6V2MP7IG","created_at":"2026-07-05T04:55:01.223217+00:00"},{"alias_kind":"pith_short_8","alias_value":"U37NGQWX","created_at":"2026-07-05T04:55:01.223217+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/U37NGQWX6V2MP7IGW4WX4J3IVZ","json":"https://pith.science/pith/U37NGQWX6V2MP7IGW4WX4J3IVZ.json","graph_json":"https://pith.science/api/pith-number/U37NGQWX6V2MP7IGW4WX4J3IVZ/graph.json","events_json":"https://pith.science/api/pith-number/U37NGQWX6V2MP7IGW4WX4J3IVZ/events.json","paper":"https://pith.science/paper/U37NGQWX"},"agent_actions":{"view_html":"https://pith.science/pith/U37NGQWX6V2MP7IGW4WX4J3IVZ","download_json":"https://pith.science/pith/U37NGQWX6V2MP7IGW4WX4J3IVZ.json","view_paper":"https://pith.science/paper/U37NGQWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08084&json=true","fetch_graph":"https://pith.science/api/pith-number/U37NGQWX6V2MP7IGW4WX4J3IVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/U37NGQWX6V2MP7IGW4WX4J3IVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U37NGQWX6V2MP7IGW4WX4J3IVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U37NGQWX6V2MP7IGW4WX4J3IVZ/action/storage_attestation","attest_author":"https://pith.science/pith/U37NGQWX6V2MP7IGW4WX4J3IVZ/action/author_attestation","sign_citation":"https://pith.science/pith/U37NGQWX6V2MP7IGW4WX4J3IVZ/action/citation_signature","submit_replication":"https://pith.science/pith/U37NGQWX6V2MP7IGW4WX4J3IVZ/action/replication_record"}},"created_at":"2026-07-05T04:55:01.223217+00:00","updated_at":"2026-07-05T04:55:01.223217+00:00"}