{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FNA3CQSCQSZZ4YTVAWULMRP4RD","short_pith_number":"pith:FNA3CQSC","schema_version":"1.0","canonical_sha256":"2b41b1424284b39e627505a8b645fc88f6e2e5f249ae75741e53847435d281b2","source":{"kind":"arxiv","id":"2101.02843","version":2},"attestation_state":"computed","paper":{"title":"Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Dan Xu, Elisa Ricci, Nicu Sebe, Wanli Ouyang, Xavier Alameda-Pineda, Xiaogang Wang","submitted_at":"2021-01-08T04:14:29Z","abstract_excerpt":"Multi-scale representations deeply learned via convolutional neural networks have shown tremendous importance for various pixel-level prediction problems. In this paper we present a novel approach that advances the state of the art on pixel-level prediction in a fundamental aspect, i.e. structured multi-scale features learning and fusion. In contrast to previous works directly considering multi-scale feature maps obtained from the inner layers of a primary CNN architecture, and simply fusing the features with weighted averaging or concatenation, we propose a probabilistic graph attention netwo"},"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":"2101.02843","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-08T04:14:29Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"e210e544f9bd585a67bd2d07a8bc529a316ce66c0169c364bb318a8b27785085","abstract_canon_sha256":"ff9f2f27ffa835f03d2cd6d0e3a8b35b5bed6c77d23f82542c83a60a01235cd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:37.654340Z","signature_b64":"RqyMYzc3n/wrX/otH/haD714BWSPADJ9e/9ZGnsBch06wT5UMdWIvpmQLfaCNnHs5GrGev+F26kL9RSGcBDmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b41b1424284b39e627505a8b645fc88f6e2e5f249ae75741e53847435d281b2","last_reissued_at":"2026-07-05T04:04:37.653861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:37.653861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Dan Xu, Elisa Ricci, Nicu Sebe, Wanli Ouyang, Xavier Alameda-Pineda, Xiaogang Wang","submitted_at":"2021-01-08T04:14:29Z","abstract_excerpt":"Multi-scale representations deeply learned via convolutional neural networks have shown tremendous importance for various pixel-level prediction problems. In this paper we present a novel approach that advances the state of the art on pixel-level prediction in a fundamental aspect, i.e. structured multi-scale features learning and fusion. In contrast to previous works directly considering multi-scale feature maps obtained from the inner layers of a primary CNN architecture, and simply fusing the features with weighted averaging or concatenation, we propose a probabilistic graph attention netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.02843","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/2101.02843/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":"2101.02843","created_at":"2026-07-05T04:04:37.653918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.02843v2","created_at":"2026-07-05T04:04:37.653918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.02843","created_at":"2026-07-05T04:04:37.653918+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNA3CQSCQSZZ","created_at":"2026-07-05T04:04:37.653918+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNA3CQSCQSZZ4YTV","created_at":"2026-07-05T04:04:37.653918+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNA3CQSC","created_at":"2026-07-05T04:04:37.653918+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/FNA3CQSCQSZZ4YTVAWULMRP4RD","json":"https://pith.science/pith/FNA3CQSCQSZZ4YTVAWULMRP4RD.json","graph_json":"https://pith.science/api/pith-number/FNA3CQSCQSZZ4YTVAWULMRP4RD/graph.json","events_json":"https://pith.science/api/pith-number/FNA3CQSCQSZZ4YTVAWULMRP4RD/events.json","paper":"https://pith.science/paper/FNA3CQSC"},"agent_actions":{"view_html":"https://pith.science/pith/FNA3CQSCQSZZ4YTVAWULMRP4RD","download_json":"https://pith.science/pith/FNA3CQSCQSZZ4YTVAWULMRP4RD.json","view_paper":"https://pith.science/paper/FNA3CQSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.02843&json=true","fetch_graph":"https://pith.science/api/pith-number/FNA3CQSCQSZZ4YTVAWULMRP4RD/graph.json","fetch_events":"https://pith.science/api/pith-number/FNA3CQSCQSZZ4YTVAWULMRP4RD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNA3CQSCQSZZ4YTVAWULMRP4RD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNA3CQSCQSZZ4YTVAWULMRP4RD/action/storage_attestation","attest_author":"https://pith.science/pith/FNA3CQSCQSZZ4YTVAWULMRP4RD/action/author_attestation","sign_citation":"https://pith.science/pith/FNA3CQSCQSZZ4YTVAWULMRP4RD/action/citation_signature","submit_replication":"https://pith.science/pith/FNA3CQSCQSZZ4YTVAWULMRP4RD/action/replication_record"}},"created_at":"2026-07-05T04:04:37.653918+00:00","updated_at":"2026-07-05T04:04:37.653918+00:00"}