{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:F3VUCQID6MDHQECJYRASAJOHRL","short_pith_number":"pith:F3VUCQID","schema_version":"1.0","canonical_sha256":"2eeb414103f306781049c4412025c78ad6441cd29be3e7f5718c296642f4dfe0","source":{"kind":"arxiv","id":"1708.02031","version":1},"attestation_state":"computed","paper":{"title":"Learning Uncertain Convolutional Features for Accurate Saliency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baocai Yin, Dong Wang, Hongyu Wang, Huchuan Lu, Pingping Zhang","submitted_at":"2017-08-07T08:18:04Z","abstract_excerpt":"Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key contribution of this work is to learn deep uncertain convolutional features (UCF), which encourage the robustness and accuracy of saliency detection. We achieve this via introducing a reformulated dropout (R-dropout) after specific convolutional layers to construct an uncertain ensemble of internal feature units. In addition, we propose an effective hybrid upsampling m"},"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":"1708.02031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-07T08:18:04Z","cross_cats_sorted":[],"title_canon_sha256":"67b9b54cafad5710f98d5178ac7dd3f01310af490b72d22f87e397d94417931d","abstract_canon_sha256":"994e7dea26a6bf2d83c4bebe8a2d577f39dc147c64847b5c9d42dfeb742b5507"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:32.475924Z","signature_b64":"j2g8EqQILSvpKz+3O5yvq6Qyxh7GMoov8QozSnisMS3v9g1KY8MYV+RVct9AIJ37wPY+wlekL+74sXSHum2dCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eeb414103f306781049c4412025c78ad6441cd29be3e7f5718c296642f4dfe0","last_reissued_at":"2026-05-18T00:38:32.475361Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:32.475361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Uncertain Convolutional Features for Accurate Saliency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baocai Yin, Dong Wang, Hongyu Wang, Huchuan Lu, Pingping Zhang","submitted_at":"2017-08-07T08:18:04Z","abstract_excerpt":"Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key contribution of this work is to learn deep uncertain convolutional features (UCF), which encourage the robustness and accuracy of saliency detection. We achieve this via introducing a reformulated dropout (R-dropout) after specific convolutional layers to construct an uncertain ensemble of internal feature units. In addition, we propose an effective hybrid upsampling m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02031","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":""},"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":"1708.02031","created_at":"2026-05-18T00:38:32.475459+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.02031v1","created_at":"2026-05-18T00:38:32.475459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02031","created_at":"2026-05-18T00:38:32.475459+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3VUCQID6MDH","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3VUCQID6MDHQECJ","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3VUCQID","created_at":"2026-05-18T12:31:15.632608+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/F3VUCQID6MDHQECJYRASAJOHRL","json":"https://pith.science/pith/F3VUCQID6MDHQECJYRASAJOHRL.json","graph_json":"https://pith.science/api/pith-number/F3VUCQID6MDHQECJYRASAJOHRL/graph.json","events_json":"https://pith.science/api/pith-number/F3VUCQID6MDHQECJYRASAJOHRL/events.json","paper":"https://pith.science/paper/F3VUCQID"},"agent_actions":{"view_html":"https://pith.science/pith/F3VUCQID6MDHQECJYRASAJOHRL","download_json":"https://pith.science/pith/F3VUCQID6MDHQECJYRASAJOHRL.json","view_paper":"https://pith.science/paper/F3VUCQID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.02031&json=true","fetch_graph":"https://pith.science/api/pith-number/F3VUCQID6MDHQECJYRASAJOHRL/graph.json","fetch_events":"https://pith.science/api/pith-number/F3VUCQID6MDHQECJYRASAJOHRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3VUCQID6MDHQECJYRASAJOHRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3VUCQID6MDHQECJYRASAJOHRL/action/storage_attestation","attest_author":"https://pith.science/pith/F3VUCQID6MDHQECJYRASAJOHRL/action/author_attestation","sign_citation":"https://pith.science/pith/F3VUCQID6MDHQECJYRASAJOHRL/action/citation_signature","submit_replication":"https://pith.science/pith/F3VUCQID6MDHQECJYRASAJOHRL/action/replication_record"}},"created_at":"2026-05-18T00:38:32.475459+00:00","updated_at":"2026-05-18T00:38:32.475459+00:00"}