{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U5ZASQWC3MSO6XZOEAYF6MJSNM","short_pith_number":"pith:U5ZASQWC","schema_version":"1.0","canonical_sha256":"a7720942c2db24ef5f2e20305f31326b351bd9372ba954afa503a329433c7b43","source":{"kind":"arxiv","id":"2411.13056","version":2},"attestation_state":"computed","paper":{"title":"Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Cao, Jiekang Feng, Pengfei Zhu, Qilong Wang, Qinghua Hu, Quanhao Lu","submitted_at":"2024-11-20T06:08:21Z","abstract_excerpt":"The dynamic imbalance of the fore-background is a major challenge in video object counting, which is usually caused by the sparsity of target objects. This remains understudied in existing works and often leads to severe under-/over-prediction errors. To tackle this issue in video object counting, we propose a density-embedded Efficient Masked Autoencoder Counting (E-MAC) framework in this paper. To empower the model's representation ability on density regression, we develop a new $\\mathtt{D}$ensity-$\\mathtt{E}$mbedded $\\mathtt{M}$asked m$\\mathtt{O}$deling ($\\mathtt{DEMO}$) method, which first"},"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":"2411.13056","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T06:08:21Z","cross_cats_sorted":[],"title_canon_sha256":"1051be10ad2a2a5705a82dd126e5256d23909c95f799922edf1c301be6844c4d","abstract_canon_sha256":"4e9f40594107d32089e5c8f39cce4b951bac9ed91b7a1d57cfda0c7e2b7809af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:14.099903Z","signature_b64":"62dtG7+MGAdXpXt549VTqCF97/hgX5caH9B9p/c9D5HNK/NfmuRQrNfPABgMeWd7HGy9MgU89EPBcn8YZYBGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7720942c2db24ef5f2e20305f31326b351bd9372ba954afa503a329433c7b43","last_reissued_at":"2026-07-05T10:25:14.099410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:14.099410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Cao, Jiekang Feng, Pengfei Zhu, Qilong Wang, Qinghua Hu, Quanhao Lu","submitted_at":"2024-11-20T06:08:21Z","abstract_excerpt":"The dynamic imbalance of the fore-background is a major challenge in video object counting, which is usually caused by the sparsity of target objects. This remains understudied in existing works and often leads to severe under-/over-prediction errors. To tackle this issue in video object counting, we propose a density-embedded Efficient Masked Autoencoder Counting (E-MAC) framework in this paper. To empower the model's representation ability on density regression, we develop a new $\\mathtt{D}$ensity-$\\mathtt{E}$mbedded $\\mathtt{M}$asked m$\\mathtt{O}$deling ($\\mathtt{DEMO}$) method, which first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13056","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/2411.13056/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":"2411.13056","created_at":"2026-07-05T10:25:14.099464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13056v2","created_at":"2026-07-05T10:25:14.099464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13056","created_at":"2026-07-05T10:25:14.099464+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5ZASQWC3MSO","created_at":"2026-07-05T10:25:14.099464+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5ZASQWC3MSO6XZO","created_at":"2026-07-05T10:25:14.099464+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5ZASQWC","created_at":"2026-07-05T10:25:14.099464+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/U5ZASQWC3MSO6XZOEAYF6MJSNM","json":"https://pith.science/pith/U5ZASQWC3MSO6XZOEAYF6MJSNM.json","graph_json":"https://pith.science/api/pith-number/U5ZASQWC3MSO6XZOEAYF6MJSNM/graph.json","events_json":"https://pith.science/api/pith-number/U5ZASQWC3MSO6XZOEAYF6MJSNM/events.json","paper":"https://pith.science/paper/U5ZASQWC"},"agent_actions":{"view_html":"https://pith.science/pith/U5ZASQWC3MSO6XZOEAYF6MJSNM","download_json":"https://pith.science/pith/U5ZASQWC3MSO6XZOEAYF6MJSNM.json","view_paper":"https://pith.science/paper/U5ZASQWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13056&json=true","fetch_graph":"https://pith.science/api/pith-number/U5ZASQWC3MSO6XZOEAYF6MJSNM/graph.json","fetch_events":"https://pith.science/api/pith-number/U5ZASQWC3MSO6XZOEAYF6MJSNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5ZASQWC3MSO6XZOEAYF6MJSNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5ZASQWC3MSO6XZOEAYF6MJSNM/action/storage_attestation","attest_author":"https://pith.science/pith/U5ZASQWC3MSO6XZOEAYF6MJSNM/action/author_attestation","sign_citation":"https://pith.science/pith/U5ZASQWC3MSO6XZOEAYF6MJSNM/action/citation_signature","submit_replication":"https://pith.science/pith/U5ZASQWC3MSO6XZOEAYF6MJSNM/action/replication_record"}},"created_at":"2026-07-05T10:25:14.099464+00:00","updated_at":"2026-07-05T10:25:14.099464+00:00"}