{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5Q4USBML5PU67CP7HERMWXUV53","short_pith_number":"pith:5Q4USBML","schema_version":"1.0","canonical_sha256":"ec3949058bebe9ef89ff3922cb5e95eeed483666e730070194de8f377663844e","source":{"kind":"arxiv","id":"2402.15297","version":1},"attestation_state":"computed","paper":{"title":"Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Deyu Meng, Hui Lin, Rongrong Ji, Xiaopeng Hong, Yaowei Wang, Zhiheng Ma, Zhou Su","submitted_at":"2024-02-23T12:48:02Z","abstract_excerpt":"This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled. We formulate the pixel-wise density value to regress as a probability distribution, instead of a single deterministic value. On this basis, we propose a semi-supervised crowd-counting model. Firstly, we design a pixel-wise distribution matching loss to measure the differences in the pixel-wise density distributions between the prediction and the ground truth; Secondly, we enhance the transformer decoder by using density tokens to specialize the forwards of decoders w.r.t. differen"},"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":"2402.15297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-23T12:48:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c2fde43386b8c711a2d010dbedad3237478186dd004028308d20c8a3ddb43208","abstract_canon_sha256":"5bdde454af6f2b0d2c374538fd44984226851e642a9da97b43525349219383c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:38.909015Z","signature_b64":"J5zHgklMj9R4Nw6p7nfy5o+iNr6yskKT0uCdLh1qS3FOegdi7cAH2xnBQmnB/8Lg2SsuwasLzrtHihsozI/6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec3949058bebe9ef89ff3922cb5e95eeed483666e730070194de8f377663844e","last_reissued_at":"2026-07-05T07:48:38.908613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:38.908613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Deyu Meng, Hui Lin, Rongrong Ji, Xiaopeng Hong, Yaowei Wang, Zhiheng Ma, Zhou Su","submitted_at":"2024-02-23T12:48:02Z","abstract_excerpt":"This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled. We formulate the pixel-wise density value to regress as a probability distribution, instead of a single deterministic value. On this basis, we propose a semi-supervised crowd-counting model. Firstly, we design a pixel-wise distribution matching loss to measure the differences in the pixel-wise density distributions between the prediction and the ground truth; Secondly, we enhance the transformer decoder by using density tokens to specialize the forwards of decoders w.r.t. differen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15297","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/2402.15297/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":"2402.15297","created_at":"2026-07-05T07:48:38.908669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15297v1","created_at":"2026-07-05T07:48:38.908669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15297","created_at":"2026-07-05T07:48:38.908669+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Q4USBML5PU6","created_at":"2026-07-05T07:48:38.908669+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Q4USBML5PU67CP7","created_at":"2026-07-05T07:48:38.908669+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Q4USBML","created_at":"2026-07-05T07:48:38.908669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21943","citing_title":"Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Q4USBML5PU67CP7HERMWXUV53","json":"https://pith.science/pith/5Q4USBML5PU67CP7HERMWXUV53.json","graph_json":"https://pith.science/api/pith-number/5Q4USBML5PU67CP7HERMWXUV53/graph.json","events_json":"https://pith.science/api/pith-number/5Q4USBML5PU67CP7HERMWXUV53/events.json","paper":"https://pith.science/paper/5Q4USBML"},"agent_actions":{"view_html":"https://pith.science/pith/5Q4USBML5PU67CP7HERMWXUV53","download_json":"https://pith.science/pith/5Q4USBML5PU67CP7HERMWXUV53.json","view_paper":"https://pith.science/paper/5Q4USBML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15297&json=true","fetch_graph":"https://pith.science/api/pith-number/5Q4USBML5PU67CP7HERMWXUV53/graph.json","fetch_events":"https://pith.science/api/pith-number/5Q4USBML5PU67CP7HERMWXUV53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Q4USBML5PU67CP7HERMWXUV53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Q4USBML5PU67CP7HERMWXUV53/action/storage_attestation","attest_author":"https://pith.science/pith/5Q4USBML5PU67CP7HERMWXUV53/action/author_attestation","sign_citation":"https://pith.science/pith/5Q4USBML5PU67CP7HERMWXUV53/action/citation_signature","submit_replication":"https://pith.science/pith/5Q4USBML5PU67CP7HERMWXUV53/action/replication_record"}},"created_at":"2026-07-05T07:48:38.908669+00:00","updated_at":"2026-07-05T07:48:38.908669+00:00"}