{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3Z3VEXTKALCNPL3TGNPNMUJEA3","short_pith_number":"pith:3Z3VEXTK","schema_version":"1.0","canonical_sha256":"de77525e6a02c4d7af73335ed6512406f1356f10c5f1df40697bb563236c62b1","source":{"kind":"arxiv","id":"1907.08051","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Training of Proposal-based Segmentation via Background Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Helge Rhodin, Isinsu Katircioglu, J\\\"org Sp\\\"orri, Mathieu Salzmann, Pascal Fua, Victor Constantin","submitted_at":"2019-07-18T13:52:06Z","abstract_excerpt":"While supervised object detection methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this in scenarios where annotating data is prohibitively expensive, we introduce a self-supervised approach to object detection and segmentation, able to work with monocular images captured with a moving camera. At the heart of our approach lies the observation that segmentation and background reconstruction are linked tasks, and the idea that, because we observe a structured scene, background regions "},"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":"1907.08051","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-18T13:52:06Z","cross_cats_sorted":[],"title_canon_sha256":"218c0a07562b7be77e49d97733b6c661d39cbfd89058020e9ccab6ea0b7d66bd","abstract_canon_sha256":"c44c3359ad5b67d7cb6b2978ab82dcbf1baf7a790e14257bd60a91d5d15c0a37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:15.284902Z","signature_b64":"n4hXNcXzkYdRycqAR9YRMVVPGGME6fyzNKvodHkjE1vu02i8lx/6SRVvloDv1J2sgqk4W9Vy50IBcUNxvRh+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de77525e6a02c4d7af73335ed6512406f1356f10c5f1df40697bb563236c62b1","last_reissued_at":"2026-05-17T23:40:15.284224Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:15.284224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Training of Proposal-based Segmentation via Background Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Helge Rhodin, Isinsu Katircioglu, J\\\"org Sp\\\"orri, Mathieu Salzmann, Pascal Fua, Victor Constantin","submitted_at":"2019-07-18T13:52:06Z","abstract_excerpt":"While supervised object detection methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this in scenarios where annotating data is prohibitively expensive, we introduce a self-supervised approach to object detection and segmentation, able to work with monocular images captured with a moving camera. At the heart of our approach lies the observation that segmentation and background reconstruction are linked tasks, and the idea that, because we observe a structured scene, background regions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08051","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":"1907.08051","created_at":"2026-05-17T23:40:15.284331+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.08051v1","created_at":"2026-05-17T23:40:15.284331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08051","created_at":"2026-05-17T23:40:15.284331+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Z3VEXTKALCN","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Z3VEXTKALCNPL3T","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Z3VEXTK","created_at":"2026-05-18T12:33:10.108867+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/3Z3VEXTKALCNPL3TGNPNMUJEA3","json":"https://pith.science/pith/3Z3VEXTKALCNPL3TGNPNMUJEA3.json","graph_json":"https://pith.science/api/pith-number/3Z3VEXTKALCNPL3TGNPNMUJEA3/graph.json","events_json":"https://pith.science/api/pith-number/3Z3VEXTKALCNPL3TGNPNMUJEA3/events.json","paper":"https://pith.science/paper/3Z3VEXTK"},"agent_actions":{"view_html":"https://pith.science/pith/3Z3VEXTKALCNPL3TGNPNMUJEA3","download_json":"https://pith.science/pith/3Z3VEXTKALCNPL3TGNPNMUJEA3.json","view_paper":"https://pith.science/paper/3Z3VEXTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.08051&json=true","fetch_graph":"https://pith.science/api/pith-number/3Z3VEXTKALCNPL3TGNPNMUJEA3/graph.json","fetch_events":"https://pith.science/api/pith-number/3Z3VEXTKALCNPL3TGNPNMUJEA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Z3VEXTKALCNPL3TGNPNMUJEA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Z3VEXTKALCNPL3TGNPNMUJEA3/action/storage_attestation","attest_author":"https://pith.science/pith/3Z3VEXTKALCNPL3TGNPNMUJEA3/action/author_attestation","sign_citation":"https://pith.science/pith/3Z3VEXTKALCNPL3TGNPNMUJEA3/action/citation_signature","submit_replication":"https://pith.science/pith/3Z3VEXTKALCNPL3TGNPNMUJEA3/action/replication_record"}},"created_at":"2026-05-17T23:40:15.284331+00:00","updated_at":"2026-05-17T23:40:15.284331+00:00"}