{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KBZXEVP4HH7M3E7KUV6BLHOUIK","short_pith_number":"pith:KBZXEVP4","schema_version":"1.0","canonical_sha256":"50737255fc39fecd93eaa57c159dd4429a5089d7418689f88ab119c96fbc77dd","source":{"kind":"arxiv","id":"2304.04231","version":1},"attestation_state":"computed","paper":{"title":"CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Liang, Jiahao Xie, Wei Xu, Xiang Bai, Xiaoqing Ye, Zhikang Zou","submitted_at":"2023-04-09T12:56:54Z","abstract_excerpt":"Supervised crowd counting relies heavily on costly manual labeling, which is difficult and expensive, especially in dense scenes. To alleviate the problem, we propose a novel unsupervised framework for crowd counting, named CrowdCLIP. The core idea is built on two observations: 1) the recent contrastive pre-trained vision-language model (CLIP) has presented impressive performance on various downstream tasks; 2) there is a natural mapping between crowd patches and count text. To the best of our knowledge, CrowdCLIP is the first to investigate the vision language knowledge to solve the counting "},"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":"2304.04231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-09T12:56:54Z","cross_cats_sorted":[],"title_canon_sha256":"fe9b130c307b7ef920f0cc9c9b388fb20900d3c2a56fb5fcd9b9ff4defead7d1","abstract_canon_sha256":"eb166ab49f4e27aa8c762bf0cd617d40c7425160e4b726e25dd20f17a19c9ceb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:13.652171Z","signature_b64":"7Qa5B9cFWO/W1Qjejln8hUZ8wbyqbc/qabQj6GzxZbfPZAiNdujB+6BvoOsXBV1aHtgsg++UEhSefCOva2ZUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50737255fc39fecd93eaa57c159dd4429a5089d7418689f88ab119c96fbc77dd","last_reissued_at":"2026-07-05T05:59:13.651689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:13.651689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Liang, Jiahao Xie, Wei Xu, Xiang Bai, Xiaoqing Ye, Zhikang Zou","submitted_at":"2023-04-09T12:56:54Z","abstract_excerpt":"Supervised crowd counting relies heavily on costly manual labeling, which is difficult and expensive, especially in dense scenes. To alleviate the problem, we propose a novel unsupervised framework for crowd counting, named CrowdCLIP. The core idea is built on two observations: 1) the recent contrastive pre-trained vision-language model (CLIP) has presented impressive performance on various downstream tasks; 2) there is a natural mapping between crowd patches and count text. To the best of our knowledge, CrowdCLIP is the first to investigate the vision language knowledge to solve the counting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04231","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/2304.04231/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":"2304.04231","created_at":"2026-07-05T05:59:13.651749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04231v1","created_at":"2026-07-05T05:59:13.651749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04231","created_at":"2026-07-05T05:59:13.651749+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBZXEVP4HH7M","created_at":"2026-07-05T05:59:13.651749+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBZXEVP4HH7M3E7K","created_at":"2026-07-05T05:59:13.651749+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBZXEVP4","created_at":"2026-07-05T05:59:13.651749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03683","citing_title":"On the rankability of visual embeddings","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBZXEVP4HH7M3E7KUV6BLHOUIK","json":"https://pith.science/pith/KBZXEVP4HH7M3E7KUV6BLHOUIK.json","graph_json":"https://pith.science/api/pith-number/KBZXEVP4HH7M3E7KUV6BLHOUIK/graph.json","events_json":"https://pith.science/api/pith-number/KBZXEVP4HH7M3E7KUV6BLHOUIK/events.json","paper":"https://pith.science/paper/KBZXEVP4"},"agent_actions":{"view_html":"https://pith.science/pith/KBZXEVP4HH7M3E7KUV6BLHOUIK","download_json":"https://pith.science/pith/KBZXEVP4HH7M3E7KUV6BLHOUIK.json","view_paper":"https://pith.science/paper/KBZXEVP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04231&json=true","fetch_graph":"https://pith.science/api/pith-number/KBZXEVP4HH7M3E7KUV6BLHOUIK/graph.json","fetch_events":"https://pith.science/api/pith-number/KBZXEVP4HH7M3E7KUV6BLHOUIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBZXEVP4HH7M3E7KUV6BLHOUIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBZXEVP4HH7M3E7KUV6BLHOUIK/action/storage_attestation","attest_author":"https://pith.science/pith/KBZXEVP4HH7M3E7KUV6BLHOUIK/action/author_attestation","sign_citation":"https://pith.science/pith/KBZXEVP4HH7M3E7KUV6BLHOUIK/action/citation_signature","submit_replication":"https://pith.science/pith/KBZXEVP4HH7M3E7KUV6BLHOUIK/action/replication_record"}},"created_at":"2026-07-05T05:59:13.651749+00:00","updated_at":"2026-07-05T05:59:13.651749+00:00"}