{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2WYZUGPSXXMU3RN33VN7JQGE2L","short_pith_number":"pith:2WYZUGPS","schema_version":"1.0","canonical_sha256":"d5b19a19f2bdd94dc5bbdd5bf4c0c4d2eafa55de3d62122c0d2281628ad76b81","source":{"kind":"arxiv","id":"2608.06236","version":1},"attestation_state":"computed","paper":{"title":"Depth-Guided Video Object Counting in Crowded Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Antoni B. Chan, Linhao Zhang, Weidong Chen, Weigang Zhang, Xinyan Liu, Yuanjing Xu, Zhuangzhe Meng, Zixuan Zou","submitted_at":"2026-08-06T16:24:41Z","abstract_excerpt":"Our primary objective is to advance video object counting in crowded scenes, aiming to robustly count all instances of a target category based on given text or visual prompts. Existing methods rely on RGB information, limiting their discriminative ability in crowded and occluded conditions. To address this, we propose a Depth-Guided Detector (DG-Det) along with a general post-processing pipeline. By integrating depth cues with multi-scale RGB-D cross-attention and explicit occlusion prediction, our method enhances spatial understanding and achieves robust detection in crowded and occluded scen"},"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":"2608.06236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T16:24:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2509bbb2f6af19d7dec23b19ff0f7f86a77dca9844998c86ec9dc3345d6510f5","abstract_canon_sha256":"220bc322b9e9a625a8dc5d49c72c692ed776c46c6b7469d780ca9d2f3636778b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T01:41:00.656954Z","signature_b64":"3xL8wgxrXHNiBZoDrDfdFMaPKnRZ/Ys3YnCwHlZbH6lthGnY0f86eO3jCycK5ShggBexlMAkJWzf8hsHW+aKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5b19a19f2bdd94dc5bbdd5bf4c0c4d2eafa55de3d62122c0d2281628ad76b81","last_reissued_at":"2026-08-07T01:41:00.655372Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T01:41:00.655372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Depth-Guided Video Object Counting in Crowded Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Antoni B. Chan, Linhao Zhang, Weidong Chen, Weigang Zhang, Xinyan Liu, Yuanjing Xu, Zhuangzhe Meng, Zixuan Zou","submitted_at":"2026-08-06T16:24:41Z","abstract_excerpt":"Our primary objective is to advance video object counting in crowded scenes, aiming to robustly count all instances of a target category based on given text or visual prompts. Existing methods rely on RGB information, limiting their discriminative ability in crowded and occluded conditions. To address this, we propose a Depth-Guided Detector (DG-Det) along with a general post-processing pipeline. By integrating depth cues with multi-scale RGB-D cross-attention and explicit occlusion prediction, our method enhances spatial understanding and achieves robust detection in crowded and occluded scen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06236","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/2608.06236/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":"2608.06236","created_at":"2026-08-07T01:41:00.658009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06236v1","created_at":"2026-08-07T01:41:00.658009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06236","created_at":"2026-08-07T01:41:00.658009+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WYZUGPSXXMU","created_at":"2026-08-07T01:41:00.658009+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WYZUGPSXXMU3RN3","created_at":"2026-08-07T01:41:00.658009+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WYZUGPS","created_at":"2026-08-07T01:41:00.658009+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/2WYZUGPSXXMU3RN33VN7JQGE2L","json":"https://pith.science/pith/2WYZUGPSXXMU3RN33VN7JQGE2L.json","graph_json":"https://pith.science/api/pith-number/2WYZUGPSXXMU3RN33VN7JQGE2L/graph.json","events_json":"https://pith.science/api/pith-number/2WYZUGPSXXMU3RN33VN7JQGE2L/events.json","paper":"https://pith.science/paper/2WYZUGPS"},"agent_actions":{"view_html":"https://pith.science/pith/2WYZUGPSXXMU3RN33VN7JQGE2L","download_json":"https://pith.science/pith/2WYZUGPSXXMU3RN33VN7JQGE2L.json","view_paper":"https://pith.science/paper/2WYZUGPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06236&json=true","fetch_graph":"https://pith.science/api/pith-number/2WYZUGPSXXMU3RN33VN7JQGE2L/graph.json","fetch_events":"https://pith.science/api/pith-number/2WYZUGPSXXMU3RN33VN7JQGE2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WYZUGPSXXMU3RN33VN7JQGE2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WYZUGPSXXMU3RN33VN7JQGE2L/action/storage_attestation","attest_author":"https://pith.science/pith/2WYZUGPSXXMU3RN33VN7JQGE2L/action/author_attestation","sign_citation":"https://pith.science/pith/2WYZUGPSXXMU3RN33VN7JQGE2L/action/citation_signature","submit_replication":"https://pith.science/pith/2WYZUGPSXXMU3RN33VN7JQGE2L/action/replication_record"}},"created_at":"2026-08-07T01:41:00.658009+00:00","updated_at":"2026-08-07T01:41:00.658009+00:00"}