{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5J6RRZ6ABJWMD5NV2T3EC6ZEL3","short_pith_number":"pith:5J6RRZ6A","schema_version":"1.0","canonical_sha256":"ea7d18e7c00a6cc1f5b5d4f6417b245edfd296997f3e10d7918a98332e27251c","source":{"kind":"arxiv","id":"2108.08023","version":1},"attestation_state":"computed","paper":{"title":"Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Wang, Binghui Chen, Ke Li, Lei Zhang, Pengyu Li, Wangmeng Zuo, Zhaoyi Yan","submitted_at":"2021-08-18T08:06:37Z","abstract_excerpt":"In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc. Thus, for learning a general model, training with data from multiple different datasets might be a remedy and be of great value. In this paper, we resort to the multi-domain joint learning and propose a simple but effective Domain-specific Knowledge Propagating Network (DKPNet)1 for unbiasedly learning the knowledge from multiple diverse data domains at the same time. It is mainly achieved by"},"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":"2108.08023","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-18T08:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"44cf5585753195709dfb96a8f2d3e20587768615c871528a7a4a9767259e9a7e","abstract_canon_sha256":"2d45489b59e3515c740cca0f84d310bd5ccd93a97270a56d2ea18968fa1992f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:50.891488Z","signature_b64":"FvtHWIDqNMlrHB4BPROOuNpEU0qjuEOZhRqp7Xh8auC0ubmmMmXzp0LrZlVq3JIrsWznofrLZg68Yl2LW/GUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea7d18e7c00a6cc1f5b5d4f6417b245edfd296997f3e10d7918a98332e27251c","last_reissued_at":"2026-07-05T03:06:50.891069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:50.891069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Wang, Binghui Chen, Ke Li, Lei Zhang, Pengyu Li, Wangmeng Zuo, Zhaoyi Yan","submitted_at":"2021-08-18T08:06:37Z","abstract_excerpt":"In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc. Thus, for learning a general model, training with data from multiple different datasets might be a remedy and be of great value. In this paper, we resort to the multi-domain joint learning and propose a simple but effective Domain-specific Knowledge Propagating Network (DKPNet)1 for unbiasedly learning the knowledge from multiple diverse data domains at the same time. It is mainly achieved by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08023","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/2108.08023/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":"2108.08023","created_at":"2026-07-05T03:06:50.891135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.08023v1","created_at":"2026-07-05T03:06:50.891135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08023","created_at":"2026-07-05T03:06:50.891135+00:00"},{"alias_kind":"pith_short_12","alias_value":"5J6RRZ6ABJWM","created_at":"2026-07-05T03:06:50.891135+00:00"},{"alias_kind":"pith_short_16","alias_value":"5J6RRZ6ABJWMD5NV","created_at":"2026-07-05T03:06:50.891135+00:00"},{"alias_kind":"pith_short_8","alias_value":"5J6RRZ6A","created_at":"2026-07-05T03:06:50.891135+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/5J6RRZ6ABJWMD5NV2T3EC6ZEL3","json":"https://pith.science/pith/5J6RRZ6ABJWMD5NV2T3EC6ZEL3.json","graph_json":"https://pith.science/api/pith-number/5J6RRZ6ABJWMD5NV2T3EC6ZEL3/graph.json","events_json":"https://pith.science/api/pith-number/5J6RRZ6ABJWMD5NV2T3EC6ZEL3/events.json","paper":"https://pith.science/paper/5J6RRZ6A"},"agent_actions":{"view_html":"https://pith.science/pith/5J6RRZ6ABJWMD5NV2T3EC6ZEL3","download_json":"https://pith.science/pith/5J6RRZ6ABJWMD5NV2T3EC6ZEL3.json","view_paper":"https://pith.science/paper/5J6RRZ6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.08023&json=true","fetch_graph":"https://pith.science/api/pith-number/5J6RRZ6ABJWMD5NV2T3EC6ZEL3/graph.json","fetch_events":"https://pith.science/api/pith-number/5J6RRZ6ABJWMD5NV2T3EC6ZEL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5J6RRZ6ABJWMD5NV2T3EC6ZEL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5J6RRZ6ABJWMD5NV2T3EC6ZEL3/action/storage_attestation","attest_author":"https://pith.science/pith/5J6RRZ6ABJWMD5NV2T3EC6ZEL3/action/author_attestation","sign_citation":"https://pith.science/pith/5J6RRZ6ABJWMD5NV2T3EC6ZEL3/action/citation_signature","submit_replication":"https://pith.science/pith/5J6RRZ6ABJWMD5NV2T3EC6ZEL3/action/replication_record"}},"created_at":"2026-07-05T03:06:50.891135+00:00","updated_at":"2026-07-05T03:06:50.891135+00:00"}