{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OSIJWZCYC3XZ5R5PE43MG7AH5B","short_pith_number":"pith:OSIJWZCY","schema_version":"1.0","canonical_sha256":"74909b645816ef9ec7af2736c37c07e870221d180b7d4240b99bac1e33d6b620","source":{"kind":"arxiv","id":"1804.09466","version":1},"attestation_state":"computed","paper":{"title":"Zigzag Learning for Weakly Supervised Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongkai Xiong, Jiashi Feng, Qi Tian, Xiaopeng Zhang","submitted_at":"2018-04-25T10:26:57Z","abstract_excerpt":"This paper addresses weakly supervised object detection with only image-level supervision at training stage. Previous approaches train detection models with entire images all at once, making the models prone to being trapped in sub-optimums due to the introduced false positive examples. Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds. Towards this goal, we first develop a criterion named mean Energy Accumulation Scores (mEAS) to automatically measure and rank localization difficulty of "},"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":"1804.09466","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-25T10:26:57Z","cross_cats_sorted":[],"title_canon_sha256":"9aa386c60310f29667fe3f639d8e5b57227389f2930ec07c03c69c63e580b4b6","abstract_canon_sha256":"cdc90a4c352056d6b4c247d78b736dc1b6391aeed14df144298e00e855cdcdb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:31.724711Z","signature_b64":"02VeT81ml/TFcBKKWRBHvYMkMMILvYn0NnPyCBr3I3mNLm1GQ9KLGvVqMNxJulOwp/5huFSaKAiepBYJkPdNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74909b645816ef9ec7af2736c37c07e870221d180b7d4240b99bac1e33d6b620","last_reissued_at":"2026-05-18T00:17:31.724174Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:31.724174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zigzag Learning for Weakly Supervised Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongkai Xiong, Jiashi Feng, Qi Tian, Xiaopeng Zhang","submitted_at":"2018-04-25T10:26:57Z","abstract_excerpt":"This paper addresses weakly supervised object detection with only image-level supervision at training stage. Previous approaches train detection models with entire images all at once, making the models prone to being trapped in sub-optimums due to the introduced false positive examples. Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds. Towards this goal, we first develop a criterion named mean Energy Accumulation Scores (mEAS) to automatically measure and rank localization difficulty of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09466","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":"1804.09466","created_at":"2026-05-18T00:17:31.724253+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.09466v1","created_at":"2026-05-18T00:17:31.724253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09466","created_at":"2026-05-18T00:17:31.724253+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSIJWZCYC3XZ","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSIJWZCYC3XZ5R5P","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSIJWZCY","created_at":"2026-05-18T12:32:43.782077+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/OSIJWZCYC3XZ5R5PE43MG7AH5B","json":"https://pith.science/pith/OSIJWZCYC3XZ5R5PE43MG7AH5B.json","graph_json":"https://pith.science/api/pith-number/OSIJWZCYC3XZ5R5PE43MG7AH5B/graph.json","events_json":"https://pith.science/api/pith-number/OSIJWZCYC3XZ5R5PE43MG7AH5B/events.json","paper":"https://pith.science/paper/OSIJWZCY"},"agent_actions":{"view_html":"https://pith.science/pith/OSIJWZCYC3XZ5R5PE43MG7AH5B","download_json":"https://pith.science/pith/OSIJWZCYC3XZ5R5PE43MG7AH5B.json","view_paper":"https://pith.science/paper/OSIJWZCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.09466&json=true","fetch_graph":"https://pith.science/api/pith-number/OSIJWZCYC3XZ5R5PE43MG7AH5B/graph.json","fetch_events":"https://pith.science/api/pith-number/OSIJWZCYC3XZ5R5PE43MG7AH5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSIJWZCYC3XZ5R5PE43MG7AH5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSIJWZCYC3XZ5R5PE43MG7AH5B/action/storage_attestation","attest_author":"https://pith.science/pith/OSIJWZCYC3XZ5R5PE43MG7AH5B/action/author_attestation","sign_citation":"https://pith.science/pith/OSIJWZCYC3XZ5R5PE43MG7AH5B/action/citation_signature","submit_replication":"https://pith.science/pith/OSIJWZCYC3XZ5R5PE43MG7AH5B/action/replication_record"}},"created_at":"2026-05-18T00:17:31.724253+00:00","updated_at":"2026-05-18T00:17:31.724253+00:00"}