{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:755A5TWAKZBHF2IBFG7GC7AG24","short_pith_number":"pith:755A5TWA","schema_version":"1.0","canonical_sha256":"ff7a0ecec0564272e90129be617c06d72eeea999da8b64b78bec809bbfec2792","source":{"kind":"arxiv","id":"1803.09859","version":1},"attestation_state":"computed","paper":{"title":"WebSeg: Learning Semantic Segmentation from Web Searches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangjiang Liu, Ming-Ming Cheng, Philip H.S. Torr, Qibin Hou","submitted_at":"2018-03-27T02:59:13Z","abstract_excerpt":"In this paper, we improve semantic segmentation by automatically learning from Flickr images associated with a particular keyword, without relying on any explicit user annotations, thus substantially alleviating the dependence on accurate annotations when compared to previous weakly supervised methods.\n  To solve such a challenging problem, we leverage several low-level cues (such as saliency, edges, etc.) to help generate a proxy ground truth. Due to the diversity of web-crawled images, we anticipate a large amount of 'label noise' in which other objects might be present. We design an online "},"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":"1803.09859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T02:59:13Z","cross_cats_sorted":[],"title_canon_sha256":"e37ba40e4630bfaeb9c3b2515d8f56310f519f4df7b33626c3d9b1dc9c914edc","abstract_canon_sha256":"8ab62b41b1bb3a080febc6936cd6a13f86420cc710441e31f4b6708767f7a99d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:10.265675Z","signature_b64":"mCvAosclH0XBu0Ck3bmSpVf14bR42D0WhJ4cP+oxwhaywhYddhSoiXKHG5mCn82z0YFBZqzGP3mhE8Q23wExAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff7a0ecec0564272e90129be617c06d72eeea999da8b64b78bec809bbfec2792","last_reissued_at":"2026-05-18T00:20:10.265001Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:10.265001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebSeg: Learning Semantic Segmentation from Web Searches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangjiang Liu, Ming-Ming Cheng, Philip H.S. Torr, Qibin Hou","submitted_at":"2018-03-27T02:59:13Z","abstract_excerpt":"In this paper, we improve semantic segmentation by automatically learning from Flickr images associated with a particular keyword, without relying on any explicit user annotations, thus substantially alleviating the dependence on accurate annotations when compared to previous weakly supervised methods.\n  To solve such a challenging problem, we leverage several low-level cues (such as saliency, edges, etc.) to help generate a proxy ground truth. Due to the diversity of web-crawled images, we anticipate a large amount of 'label noise' in which other objects might be present. We design an online "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09859","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":"1803.09859","created_at":"2026-05-18T00:20:10.265092+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.09859v1","created_at":"2026-05-18T00:20:10.265092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09859","created_at":"2026-05-18T00:20:10.265092+00:00"},{"alias_kind":"pith_short_12","alias_value":"755A5TWAKZBH","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"755A5TWAKZBHF2IB","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"755A5TWA","created_at":"2026-05-18T12:32:11.075285+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":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/755A5TWAKZBHF2IBFG7GC7AG24","json":"https://pith.science/pith/755A5TWAKZBHF2IBFG7GC7AG24.json","graph_json":"https://pith.science/api/pith-number/755A5TWAKZBHF2IBFG7GC7AG24/graph.json","events_json":"https://pith.science/api/pith-number/755A5TWAKZBHF2IBFG7GC7AG24/events.json","paper":"https://pith.science/paper/755A5TWA"},"agent_actions":{"view_html":"https://pith.science/pith/755A5TWAKZBHF2IBFG7GC7AG24","download_json":"https://pith.science/pith/755A5TWAKZBHF2IBFG7GC7AG24.json","view_paper":"https://pith.science/paper/755A5TWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.09859&json=true","fetch_graph":"https://pith.science/api/pith-number/755A5TWAKZBHF2IBFG7GC7AG24/graph.json","fetch_events":"https://pith.science/api/pith-number/755A5TWAKZBHF2IBFG7GC7AG24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/755A5TWAKZBHF2IBFG7GC7AG24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/755A5TWAKZBHF2IBFG7GC7AG24/action/storage_attestation","attest_author":"https://pith.science/pith/755A5TWAKZBHF2IBFG7GC7AG24/action/author_attestation","sign_citation":"https://pith.science/pith/755A5TWAKZBHF2IBFG7GC7AG24/action/citation_signature","submit_replication":"https://pith.science/pith/755A5TWAKZBHF2IBFG7GC7AG24/action/replication_record"}},"created_at":"2026-05-18T00:20:10.265092+00:00","updated_at":"2026-05-18T00:20:10.265092+00:00"}