{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YXLLHMPTVGOPO23MCTU7PE4EMJ","short_pith_number":"pith:YXLLHMPT","schema_version":"1.0","canonical_sha256":"c5d6b3b1f3a99cf76b6c14e9f7938462739dcfc53f6f44736e72aed198a30373","source":{"kind":"arxiv","id":"1909.06121","version":3},"attestation_state":"computed","paper":{"title":"Dual Graph Convolutional Network for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Arnab, Kuiyuan Yang, Li Zhang, Philip H.S. Torr, Xiangtai Li, Yunhai Tong","submitted_at":"2019-09-13T10:06:55Z","abstract_excerpt":"Exploiting long-range contextual information is key for pixel-wise prediction tasks such as semantic segmentation. In contrast to previous work that uses multi-scale feature fusion or dilated convolutions, we propose a novel graph-convolutional network (GCN) to address this problem. Our Dual Graph Convolutional Network (DGCNet) models the global context of the input feature by modelling two orthogonal graphs in a single framework. The first component models spatial relationships between pixels in the image, whilst the second models interdependencies along the channel dimensions of the network'"},"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":"1909.06121","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-13T10:06:55Z","cross_cats_sorted":[],"title_canon_sha256":"68db097505359a9471252eb0db1f1035fd1f147601c909260972c8834e58b9c5","abstract_canon_sha256":"d62752146cb1f25508c3dfc43fd468f67dd03b8255e36786d703046a9e18f12a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:30:38.716297Z","signature_b64":"2miqOuoFuDMyIjEJkyewOC46bno2PUCXJ3tV5LXMiWYIzjeepbu8rlG3sZ6aSSnWN1RgfK6+5CpLkgvClZ4NDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5d6b3b1f3a99cf76b6c14e9f7938462739dcfc53f6f44736e72aed198a30373","last_reissued_at":"2026-07-05T01:30:38.715877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:30:38.715877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Graph Convolutional Network for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Arnab, Kuiyuan Yang, Li Zhang, Philip H.S. Torr, Xiangtai Li, Yunhai Tong","submitted_at":"2019-09-13T10:06:55Z","abstract_excerpt":"Exploiting long-range contextual information is key for pixel-wise prediction tasks such as semantic segmentation. In contrast to previous work that uses multi-scale feature fusion or dilated convolutions, we propose a novel graph-convolutional network (GCN) to address this problem. Our Dual Graph Convolutional Network (DGCNet) models the global context of the input feature by modelling two orthogonal graphs in a single framework. The first component models spatial relationships between pixels in the image, whilst the second models interdependencies along the channel dimensions of the network'"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06121","kind":"arxiv","version":3},"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/1909.06121/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":"1909.06121","created_at":"2026-07-05T01:30:38.715940+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.06121v3","created_at":"2026-07-05T01:30:38.715940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06121","created_at":"2026-07-05T01:30:38.715940+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXLLHMPTVGOP","created_at":"2026-07-05T01:30:38.715940+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXLLHMPTVGOPO23M","created_at":"2026-07-05T01:30:38.715940+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXLLHMPT","created_at":"2026-07-05T01:30:38.715940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03197","citing_title":"Neovascularization Segmentation via a Multilateral Interaction-Enhanced Graph Convolutional Network","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YXLLHMPTVGOPO23MCTU7PE4EMJ","json":"https://pith.science/pith/YXLLHMPTVGOPO23MCTU7PE4EMJ.json","graph_json":"https://pith.science/api/pith-number/YXLLHMPTVGOPO23MCTU7PE4EMJ/graph.json","events_json":"https://pith.science/api/pith-number/YXLLHMPTVGOPO23MCTU7PE4EMJ/events.json","paper":"https://pith.science/paper/YXLLHMPT"},"agent_actions":{"view_html":"https://pith.science/pith/YXLLHMPTVGOPO23MCTU7PE4EMJ","download_json":"https://pith.science/pith/YXLLHMPTVGOPO23MCTU7PE4EMJ.json","view_paper":"https://pith.science/paper/YXLLHMPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.06121&json=true","fetch_graph":"https://pith.science/api/pith-number/YXLLHMPTVGOPO23MCTU7PE4EMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YXLLHMPTVGOPO23MCTU7PE4EMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXLLHMPTVGOPO23MCTU7PE4EMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXLLHMPTVGOPO23MCTU7PE4EMJ/action/storage_attestation","attest_author":"https://pith.science/pith/YXLLHMPTVGOPO23MCTU7PE4EMJ/action/author_attestation","sign_citation":"https://pith.science/pith/YXLLHMPTVGOPO23MCTU7PE4EMJ/action/citation_signature","submit_replication":"https://pith.science/pith/YXLLHMPTVGOPO23MCTU7PE4EMJ/action/replication_record"}},"created_at":"2026-07-05T01:30:38.715940+00:00","updated_at":"2026-07-05T01:30:38.715940+00:00"}