{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YSYX45NWBQFQQXZMV77VIDK624","short_pith_number":"pith:YSYX45NW","schema_version":"1.0","canonical_sha256":"c4b17e75b60c0b085f2cafff540d5ed729108d0825da7480728ba5d16ae86e91","source":{"kind":"arxiv","id":"2305.07304","version":2},"attestation_state":"computed","paper":{"title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","license":"","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changwen Chen, Lingbo Liu, Ruixiang Jiang","submitted_at":"2023-05-12T08:19:39Z","abstract_excerpt":"Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmentation. Adapting these models for object counting, however, remains a formidable challenge. In this study, we first investigate transferring vision-language models (VLMs) for class-agnostic object counting. Specifically, we propose CLIP-Count, the first end-to-end pipeline that estimates density maps for open-vocabulary objects with text guidance in a zero-shot manner. To align the text embedding with dense visual feat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":true,"weak_author_claims":0,"strong_author_claims":1,"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":"2305.07304","kind":"arxiv","version":2},"metadata":{"license":"","primary_cat":"cs.CV","submitted_at":"2023-05-12T08:19:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"12a5e5b94e83d43efcc36cb62a84823e908bf8d6533bad910ccad73c835d55c6","abstract_canon_sha256":"fc2346a3375978cb75068a8db9261adae2df56db0ad24b8b5b2ef576233f9583"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-28T15:26:19.553885Z","signature_b64":"LTVhXWQZhoT4jQfW4LT4J9EOIS3cZfI20Ew4yNBHfvesup89sJsRGKnJ24cvtYgSlWFpTQ9iVog3xfJX5uQBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4b17e75b60c0b085f2cafff540d5ed729108d0825da7480728ba5d16ae86e91","last_reissued_at":"2026-06-28T15:26:19.553355Z","signature_status":"signed_v1","first_computed_at":"2026-06-28T15:26:19.553355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","license":"","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changwen Chen, Lingbo Liu, Ruixiang Jiang","submitted_at":"2023-05-12T08:19:39Z","abstract_excerpt":"Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmentation. Adapting these models for object counting, however, remains a formidable challenge. In this study, we first investigate transferring vision-language models (VLMs) for class-agnostic object counting. Specifically, we propose CLIP-Count, the first end-to-end pipeline that estimates density maps for open-vocabulary objects with text guidance in a zero-shot manner. To align the text embedding with dense visual feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07304","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/2305.07304/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":"2305.07304","created_at":"2026-06-28T15:26:19.553417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.07304v2","created_at":"2026-06-28T15:26:19.553417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07304","created_at":"2026-06-28T15:26:19.553417+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSYX45NWBQFQ","created_at":"2026-06-28T15:26:19.553417+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSYX45NWBQFQQXZM","created_at":"2026-06-28T15:26:19.553417+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSYX45NW","created_at":"2026-06-28T15:26:19.553417+00:00"}],"events":[],"event_summary":{},"paper_claims":[{"claim_id":"0923a629-b1e8-47d3-b643-887db04b9d89","handle":null,"display_name":"JIANG Ruixiang","verification":"orcid_verified","verification_note":"Auto-claimed from ORCID 0000-0001-8666-6767 at registration","role_label":null,"open_disputes":0}],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSYX45NWBQFQQXZMV77VIDK624","json":"https://pith.science/pith/YSYX45NWBQFQQXZMV77VIDK624.json","graph_json":"https://pith.science/api/pith-number/YSYX45NWBQFQQXZMV77VIDK624/graph.json","events_json":"https://pith.science/api/pith-number/YSYX45NWBQFQQXZMV77VIDK624/events.json","paper":"https://pith.science/paper/YSYX45NW"},"agent_actions":{"view_html":"https://pith.science/pith/YSYX45NWBQFQQXZMV77VIDK624","download_json":"https://pith.science/pith/YSYX45NWBQFQQXZMV77VIDK624.json","view_paper":"https://pith.science/paper/YSYX45NW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.07304&json=true","fetch_graph":"https://pith.science/api/pith-number/YSYX45NWBQFQQXZMV77VIDK624/graph.json","fetch_events":"https://pith.science/api/pith-number/YSYX45NWBQFQQXZMV77VIDK624/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSYX45NWBQFQQXZMV77VIDK624/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSYX45NWBQFQQXZMV77VIDK624/action/storage_attestation","attest_author":"https://pith.science/pith/YSYX45NWBQFQQXZMV77VIDK624/action/author_attestation","sign_citation":"https://pith.science/pith/YSYX45NWBQFQQXZMV77VIDK624/action/citation_signature","submit_replication":"https://pith.science/pith/YSYX45NWBQFQQXZMV77VIDK624/action/replication_record"}},"created_at":"2026-06-28T15:26:19.553417+00:00","updated_at":"2026-06-28T15:26:19.553417+00:00"}