{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JEAABM75SRXIOYFMXL2O4V7GFE","short_pith_number":"pith:JEAABM75","schema_version":"1.0","canonical_sha256":"490000b3fd946e8760acbaf4ee57e6291e641cc81d6ab999127499dde96888f1","source":{"kind":"arxiv","id":"1809.02983","version":4},"attestation_state":"computed","paper":{"title":"Dual Attention Network for Scene Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haijie Tian, Hanqing Lu, Jing Liu, Jun Fu, Yongjun Bao, Yong Li, Zhiwei Fang","submitted_at":"2018-09-09T14:48:22Z","abstract_excerpt":"In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the selfattention mechanism. Unlike previous works that capture contexts by multi-scale features fusion, we propose a Dual Attention Networks (DANet) to adaptively integrate local features with their global dependencies. Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively. The position attention module selectively aggregates the features at each position by a weigh"},"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":"1809.02983","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-09T14:48:22Z","cross_cats_sorted":[],"title_canon_sha256":"51d03f594843dc86fbcd655bb41a2116010155923c7d0f3c74e16b3709aa58e1","abstract_canon_sha256":"73d64c6d9345c5943c9e228b68ff9e1c2b4b9cda9e134d519e876d024a541041"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:06.526109Z","signature_b64":"c1UwxlNHKzBGKrTeyQn2FHTrvRUXjEnIU5no4bW4V6Tupl8/anTkb2uGNIsR7pDFhxw87ffMNj2lK25RTdPZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"490000b3fd946e8760acbaf4ee57e6291e641cc81d6ab999127499dde96888f1","last_reissued_at":"2026-05-17T23:48:06.525688Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:06.525688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Attention Network for Scene Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haijie Tian, Hanqing Lu, Jing Liu, Jun Fu, Yongjun Bao, Yong Li, Zhiwei Fang","submitted_at":"2018-09-09T14:48:22Z","abstract_excerpt":"In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the selfattention mechanism. Unlike previous works that capture contexts by multi-scale features fusion, we propose a Dual Attention Networks (DANet) to adaptively integrate local features with their global dependencies. Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively. The position attention module selectively aggregates the features at each position by a weigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02983","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1809.02983","created_at":"2026-05-17T23:48:06.525761+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02983v4","created_at":"2026-05-17T23:48:06.525761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02983","created_at":"2026-05-17T23:48:06.525761+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEAABM75SRXI","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEAABM75SRXIOYFM","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEAABM75","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.00887","citing_title":"An Efficient Solution for Breast Tumor Segmentation and Classification in Ultrasound Images Using Deep Adversarial Learning","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07449","citing_title":"OGNet: Salient Object Detection with Output-guided Attention Module","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10958","citing_title":"Cross Attention Network for Semantic Segmentation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JEAABM75SRXIOYFMXL2O4V7GFE","json":"https://pith.science/pith/JEAABM75SRXIOYFMXL2O4V7GFE.json","graph_json":"https://pith.science/api/pith-number/JEAABM75SRXIOYFMXL2O4V7GFE/graph.json","events_json":"https://pith.science/api/pith-number/JEAABM75SRXIOYFMXL2O4V7GFE/events.json","paper":"https://pith.science/paper/JEAABM75"},"agent_actions":{"view_html":"https://pith.science/pith/JEAABM75SRXIOYFMXL2O4V7GFE","download_json":"https://pith.science/pith/JEAABM75SRXIOYFMXL2O4V7GFE.json","view_paper":"https://pith.science/paper/JEAABM75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02983&json=true","fetch_graph":"https://pith.science/api/pith-number/JEAABM75SRXIOYFMXL2O4V7GFE/graph.json","fetch_events":"https://pith.science/api/pith-number/JEAABM75SRXIOYFMXL2O4V7GFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEAABM75SRXIOYFMXL2O4V7GFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEAABM75SRXIOYFMXL2O4V7GFE/action/storage_attestation","attest_author":"https://pith.science/pith/JEAABM75SRXIOYFMXL2O4V7GFE/action/author_attestation","sign_citation":"https://pith.science/pith/JEAABM75SRXIOYFMXL2O4V7GFE/action/citation_signature","submit_replication":"https://pith.science/pith/JEAABM75SRXIOYFMXL2O4V7GFE/action/replication_record"}},"created_at":"2026-05-17T23:48:06.525761+00:00","updated_at":"2026-05-17T23:48:06.525761+00:00"}