{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TAEUPF44I4ZRGBNW7A7FFLS3LD","short_pith_number":"pith:TAEUPF44","schema_version":"1.0","canonical_sha256":"980947979c47331305b6f83e52ae5b58e937e9db86c5c15fd12ebaa3592583fb","source":{"kind":"arxiv","id":"1710.01020","version":1},"attestation_state":"computed","paper":{"title":"Learning Affinity via Spatial Propagation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guangyu Zhong, Jan Kautz, Jinwei Gu, Ming-Hsuan Yang, Shalini De Mello, Sifei Liu","submitted_at":"2017-10-03T08:00:15Z","abstract_excerpt":"In this paper, we propose spatial propagation networks for learning the affinity matrix for vision tasks. We show that by constructing a row/column linear propagation model, the spatially varying transformation matrix exactly constitutes an affinity matrix that models dense, global pairwise relationships of an image. Specifically, we develop a three-way connection for the linear propagation model, which (a) formulates a sparse transformation matrix, where all elements can be the output from a deep CNN, but (b) results in a dense affinity matrix that effectively models any task-specific pairwis"},"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":"1710.01020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-03T08:00:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab5336df2c2857ff34305d50542b2602b9b70ef82032e4718809281f5e8ee971","abstract_canon_sha256":"7aca08ab8812d1839ebf9efb4e21f706e369a0bb96f17cd5ee97aed0e88f55cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:45.498930Z","signature_b64":"2ajq4XTE/AHhJhh/VvEGwNSlyFRuTsJ+XV3BLdzg5tpQVDkn8d9oC23Z3kp6qiVrmayjg8aVkLOM/h4OUh7MBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"980947979c47331305b6f83e52ae5b58e937e9db86c5c15fd12ebaa3592583fb","last_reissued_at":"2026-05-18T00:33:45.498330Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:45.498330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Affinity via Spatial Propagation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guangyu Zhong, Jan Kautz, Jinwei Gu, Ming-Hsuan Yang, Shalini De Mello, Sifei Liu","submitted_at":"2017-10-03T08:00:15Z","abstract_excerpt":"In this paper, we propose spatial propagation networks for learning the affinity matrix for vision tasks. We show that by constructing a row/column linear propagation model, the spatially varying transformation matrix exactly constitutes an affinity matrix that models dense, global pairwise relationships of an image. Specifically, we develop a three-way connection for the linear propagation model, which (a) formulates a sparse transformation matrix, where all elements can be the output from a deep CNN, but (b) results in a dense affinity matrix that effectively models any task-specific pairwis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01020","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":"1710.01020","created_at":"2026-05-18T00:33:45.498428+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.01020v1","created_at":"2026-05-18T00:33:45.498428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01020","created_at":"2026-05-18T00:33:45.498428+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAEUPF44I4ZR","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAEUPF44I4ZRGBNW","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAEUPF44","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2204.13635","citing_title":"SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAEUPF44I4ZRGBNW7A7FFLS3LD","json":"https://pith.science/pith/TAEUPF44I4ZRGBNW7A7FFLS3LD.json","graph_json":"https://pith.science/api/pith-number/TAEUPF44I4ZRGBNW7A7FFLS3LD/graph.json","events_json":"https://pith.science/api/pith-number/TAEUPF44I4ZRGBNW7A7FFLS3LD/events.json","paper":"https://pith.science/paper/TAEUPF44"},"agent_actions":{"view_html":"https://pith.science/pith/TAEUPF44I4ZRGBNW7A7FFLS3LD","download_json":"https://pith.science/pith/TAEUPF44I4ZRGBNW7A7FFLS3LD.json","view_paper":"https://pith.science/paper/TAEUPF44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.01020&json=true","fetch_graph":"https://pith.science/api/pith-number/TAEUPF44I4ZRGBNW7A7FFLS3LD/graph.json","fetch_events":"https://pith.science/api/pith-number/TAEUPF44I4ZRGBNW7A7FFLS3LD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAEUPF44I4ZRGBNW7A7FFLS3LD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAEUPF44I4ZRGBNW7A7FFLS3LD/action/storage_attestation","attest_author":"https://pith.science/pith/TAEUPF44I4ZRGBNW7A7FFLS3LD/action/author_attestation","sign_citation":"https://pith.science/pith/TAEUPF44I4ZRGBNW7A7FFLS3LD/action/citation_signature","submit_replication":"https://pith.science/pith/TAEUPF44I4ZRGBNW7A7FFLS3LD/action/replication_record"}},"created_at":"2026-05-18T00:33:45.498428+00:00","updated_at":"2026-05-18T00:33:45.498428+00:00"}