{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4ZADEABTKIBL444LGD6A2D27IF","short_pith_number":"pith:4ZADEABT","schema_version":"1.0","canonical_sha256":"e6403200335202be738b30fc0d0f5f414f8797e7b6e5b09e4a9c611d1a51ae23","source":{"kind":"arxiv","id":"1905.10671","version":2},"attestation_state":"computed","paper":{"title":"DIANet: Dense-and-Implicit Attention Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Haizhao Yang, Mingfu Liang, Senwei Liang, Zhongzhan Huang","submitted_at":"2019-05-25T20:51:07Z","abstract_excerpt":"Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them into the networks. Our paper proposes a novel-and-simple framework that shares an attention module throughout different network layers to encourage the integration of layer-wise information and this parameter-sharing module is referred as Dense-and-Implicit-Attention (DIA) unit. Many choices of modules can be used in the DIA unit. Since Long Short Term Memory (LSTM) has a capacity of capturing long-distance dependenc"},"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":"1905.10671","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-25T20:51:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3f44e57008a39e781559de51611086af7caba7686dfe44f3676770431626d0a9","abstract_canon_sha256":"d68e1afb2dbf0c8371739087ae22f6540182d2193ab59de41d2ab4f58ea55850"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:08.567227Z","signature_b64":"alycEUmDa48D9xb8sNJI+rVar3oBumCjqk+czF8sZEPDD3zmqk8Eu+Jl+P1+DugYCh/I2DIAGzqV2q3FLx9qBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6403200335202be738b30fc0d0f5f414f8797e7b6e5b09e4a9c611d1a51ae23","last_reissued_at":"2026-07-05T00:06:08.566569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:08.566569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIANet: Dense-and-Implicit Attention Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Haizhao Yang, Mingfu Liang, Senwei Liang, Zhongzhan Huang","submitted_at":"2019-05-25T20:51:07Z","abstract_excerpt":"Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them into the networks. Our paper proposes a novel-and-simple framework that shares an attention module throughout different network layers to encourage the integration of layer-wise information and this parameter-sharing module is referred as Dense-and-Implicit-Attention (DIA) unit. Many choices of modules can be used in the DIA unit. Since Long Short Term Memory (LSTM) has a capacity of capturing long-distance dependenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10671","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/1905.10671/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":"1905.10671","created_at":"2026-07-05T00:06:08.566626+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10671v2","created_at":"2026-07-05T00:06:08.566626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10671","created_at":"2026-07-05T00:06:08.566626+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZADEABTKIBL","created_at":"2026-07-05T00:06:08.566626+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZADEABTKIBL444L","created_at":"2026-07-05T00:06:08.566626+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZADEABT","created_at":"2026-07-05T00:06:08.566626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.04008","citing_title":"Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZADEABTKIBL444LGD6A2D27IF","json":"https://pith.science/pith/4ZADEABTKIBL444LGD6A2D27IF.json","graph_json":"https://pith.science/api/pith-number/4ZADEABTKIBL444LGD6A2D27IF/graph.json","events_json":"https://pith.science/api/pith-number/4ZADEABTKIBL444LGD6A2D27IF/events.json","paper":"https://pith.science/paper/4ZADEABT"},"agent_actions":{"view_html":"https://pith.science/pith/4ZADEABTKIBL444LGD6A2D27IF","download_json":"https://pith.science/pith/4ZADEABTKIBL444LGD6A2D27IF.json","view_paper":"https://pith.science/paper/4ZADEABT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10671&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZADEABTKIBL444LGD6A2D27IF/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZADEABTKIBL444LGD6A2D27IF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZADEABTKIBL444LGD6A2D27IF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZADEABTKIBL444LGD6A2D27IF/action/storage_attestation","attest_author":"https://pith.science/pith/4ZADEABTKIBL444LGD6A2D27IF/action/author_attestation","sign_citation":"https://pith.science/pith/4ZADEABTKIBL444LGD6A2D27IF/action/citation_signature","submit_replication":"https://pith.science/pith/4ZADEABTKIBL444LGD6A2D27IF/action/replication_record"}},"created_at":"2026-07-05T00:06:08.566626+00:00","updated_at":"2026-07-05T00:06:08.566626+00:00"}