{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SS3DRR5PUDHHICP3S7L4ZAEDYQ","short_pith_number":"pith:SS3DRR5P","schema_version":"1.0","canonical_sha256":"94b638c7afa0ce7409fb97d7cc8083c42c0dd9d0f4011278faf47b74684747ef","source":{"kind":"arxiv","id":"1904.01803","version":2},"attestation_state":"computed","paper":{"title":"GFF: Gated Fully Fusion for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Houlong Zhao, Kuiyuan Yang, Lei Han, Xiangtai Li, Yunhai Tong","submitted_at":"2019-04-03T07:00:16Z","abstract_excerpt":"Semantic segmentation generates comprehensive understanding of scenes through densely predicting the category for each pixel. High-level features from Deep Convolutional Neural Networks already demonstrate their effectiveness in semantic segmentation tasks, however the coarse resolution of high-level features often leads to inferior results for small/thin objects where detailed information is important. It is natural to consider importing low level features to compensate for the lost detailed information in high-level features.Unfortunately, simply combining multi-level features suffers from t"},"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":"1904.01803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-03T07:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"ba3af123abe862d5502855a2159b773a5bcf746368b9e3a407d9dcfabb085a17","abstract_canon_sha256":"452e9dca907913a1a78df69e002cee970f9a89b31f2ab412fca21dfad05a5015"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:00.281014Z","signature_b64":"6511OIyRiaywnQk+K+zc7cBoQWPmt8tcveu+fXPbjhs0hZp/kPMeps7vTYJXu0fwyzaaL1Mbw7RAIIBg+ZsfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94b638c7afa0ce7409fb97d7cc8083c42c0dd9d0f4011278faf47b74684747ef","last_reissued_at":"2026-07-05T00:43:00.280555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:00.280555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GFF: Gated Fully Fusion for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Houlong Zhao, Kuiyuan Yang, Lei Han, Xiangtai Li, Yunhai Tong","submitted_at":"2019-04-03T07:00:16Z","abstract_excerpt":"Semantic segmentation generates comprehensive understanding of scenes through densely predicting the category for each pixel. High-level features from Deep Convolutional Neural Networks already demonstrate their effectiveness in semantic segmentation tasks, however the coarse resolution of high-level features often leads to inferior results for small/thin objects where detailed information is important. It is natural to consider importing low level features to compensate for the lost detailed information in high-level features.Unfortunately, simply combining multi-level features suffers from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01803","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/1904.01803/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":"1904.01803","created_at":"2026-07-05T00:43:00.280619+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01803v2","created_at":"2026-07-05T00:43:00.280619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01803","created_at":"2026-07-05T00:43:00.280619+00:00"},{"alias_kind":"pith_short_12","alias_value":"SS3DRR5PUDHH","created_at":"2026-07-05T00:43:00.280619+00:00"},{"alias_kind":"pith_short_16","alias_value":"SS3DRR5PUDHHICP3","created_at":"2026-07-05T00:43:00.280619+00:00"},{"alias_kind":"pith_short_8","alias_value":"SS3DRR5P","created_at":"2026-07-05T00:43:00.280619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.10907","citing_title":"DFPENet-geology: A Deep Learning Framework for High Precision Recognition and Segmentation of Co-seismic Landslides","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SS3DRR5PUDHHICP3S7L4ZAEDYQ","json":"https://pith.science/pith/SS3DRR5PUDHHICP3S7L4ZAEDYQ.json","graph_json":"https://pith.science/api/pith-number/SS3DRR5PUDHHICP3S7L4ZAEDYQ/graph.json","events_json":"https://pith.science/api/pith-number/SS3DRR5PUDHHICP3S7L4ZAEDYQ/events.json","paper":"https://pith.science/paper/SS3DRR5P"},"agent_actions":{"view_html":"https://pith.science/pith/SS3DRR5PUDHHICP3S7L4ZAEDYQ","download_json":"https://pith.science/pith/SS3DRR5PUDHHICP3S7L4ZAEDYQ.json","view_paper":"https://pith.science/paper/SS3DRR5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01803&json=true","fetch_graph":"https://pith.science/api/pith-number/SS3DRR5PUDHHICP3S7L4ZAEDYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SS3DRR5PUDHHICP3S7L4ZAEDYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SS3DRR5PUDHHICP3S7L4ZAEDYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SS3DRR5PUDHHICP3S7L4ZAEDYQ/action/storage_attestation","attest_author":"https://pith.science/pith/SS3DRR5PUDHHICP3S7L4ZAEDYQ/action/author_attestation","sign_citation":"https://pith.science/pith/SS3DRR5PUDHHICP3S7L4ZAEDYQ/action/citation_signature","submit_replication":"https://pith.science/pith/SS3DRR5PUDHHICP3S7L4ZAEDYQ/action/replication_record"}},"created_at":"2026-07-05T00:43:00.280619+00:00","updated_at":"2026-07-05T00:43:00.280619+00:00"}