{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:M5OYN4BB7GJBZHM57FHRAA5NTH","short_pith_number":"pith:M5OYN4BB","schema_version":"1.0","canonical_sha256":"675d86f021f9921c9d9df94f1003ad99c27803bdd12d97a2a6a09030d5b2c01e","source":{"kind":"arxiv","id":"1811.10842","version":2},"attestation_state":"computed","paper":{"title":"CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunfeng Song, Junsong Fan, Jun Xiao, Tieniu Tan, Zhaoxiang Zhang","submitted_at":"2018-11-27T07:03:12Z","abstract_excerpt":"Weakly supervised semantic segmentation with only image-level labels saves large human effort to annotate pixel-level labels. Cutting-edge approaches rely on various innovative constraints and heuristic rules to generate the masks for every single image. Although great progress has been achieved by these methods, they treat each image independently and do not take account of the relationships across different images. In this paper, however, we argue that the cross-image relationship is vital for weakly supervised segmentation. Because it connects related regions across images, where supplement"},"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":"1811.10842","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T07:03:12Z","cross_cats_sorted":[],"title_canon_sha256":"09e64d467bb0692fc2d3cdae1dfbe9a69e0e037cb84f83048ab9b728cbb106b2","abstract_canon_sha256":"dd03d41812a328b4e740bf75b4826467c6836deb41fadef9d20517d76231b3f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:37:15.939114Z","signature_b64":"688yki4IJgml+7ue/QK2+0XgiqLddO6mGPrgr3OtwdZMdF5VU/swgP3zVptQhN7vAubvxGsXdXbSV/HLPkcnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675d86f021f9921c9d9df94f1003ad99c27803bdd12d97a2a6a09030d5b2c01e","last_reissued_at":"2026-07-05T00:37:15.938665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:37:15.938665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunfeng Song, Junsong Fan, Jun Xiao, Tieniu Tan, Zhaoxiang Zhang","submitted_at":"2018-11-27T07:03:12Z","abstract_excerpt":"Weakly supervised semantic segmentation with only image-level labels saves large human effort to annotate pixel-level labels. Cutting-edge approaches rely on various innovative constraints and heuristic rules to generate the masks for every single image. Although great progress has been achieved by these methods, they treat each image independently and do not take account of the relationships across different images. In this paper, however, we argue that the cross-image relationship is vital for weakly supervised segmentation. Because it connects related regions across images, where supplement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10842","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/1811.10842/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":"1811.10842","created_at":"2026-07-05T00:37:15.938723+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.10842v2","created_at":"2026-07-05T00:37:15.938723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10842","created_at":"2026-07-05T00:37:15.938723+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5OYN4BB7GJB","created_at":"2026-07-05T00:37:15.938723+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5OYN4BB7GJBZHM5","created_at":"2026-07-05T00:37:15.938723+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5OYN4BB","created_at":"2026-07-05T00:37:15.938723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.04501","citing_title":"Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5OYN4BB7GJBZHM57FHRAA5NTH","json":"https://pith.science/pith/M5OYN4BB7GJBZHM57FHRAA5NTH.json","graph_json":"https://pith.science/api/pith-number/M5OYN4BB7GJBZHM57FHRAA5NTH/graph.json","events_json":"https://pith.science/api/pith-number/M5OYN4BB7GJBZHM57FHRAA5NTH/events.json","paper":"https://pith.science/paper/M5OYN4BB"},"agent_actions":{"view_html":"https://pith.science/pith/M5OYN4BB7GJBZHM57FHRAA5NTH","download_json":"https://pith.science/pith/M5OYN4BB7GJBZHM57FHRAA5NTH.json","view_paper":"https://pith.science/paper/M5OYN4BB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.10842&json=true","fetch_graph":"https://pith.science/api/pith-number/M5OYN4BB7GJBZHM57FHRAA5NTH/graph.json","fetch_events":"https://pith.science/api/pith-number/M5OYN4BB7GJBZHM57FHRAA5NTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5OYN4BB7GJBZHM57FHRAA5NTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5OYN4BB7GJBZHM57FHRAA5NTH/action/storage_attestation","attest_author":"https://pith.science/pith/M5OYN4BB7GJBZHM57FHRAA5NTH/action/author_attestation","sign_citation":"https://pith.science/pith/M5OYN4BB7GJBZHM57FHRAA5NTH/action/citation_signature","submit_replication":"https://pith.science/pith/M5OYN4BB7GJBZHM57FHRAA5NTH/action/replication_record"}},"created_at":"2026-07-05T00:37:15.938723+00:00","updated_at":"2026-07-05T00:37:15.938723+00:00"}