{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EZNVINBI4BVLJTRDX6ZADEKVV2","short_pith_number":"pith:EZNVINBI","schema_version":"1.0","canonical_sha256":"265b543428e06ab4ce23bfb2019155aebd0fdd389ac514a98089aa981b2f75db","source":{"kind":"arxiv","id":"1710.10749","version":1},"attestation_state":"computed","paper":{"title":"Cascade Region Proposal and Global Context for Deep Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Li, Di Xie, Qiaoyong Zhong, Shicai Yang, Shiliang Pu, Yingying Zhang","submitted_at":"2017-10-30T03:00:04Z","abstract_excerpt":"Deep region-based object detector consists of a region proposal step and a deep object recognition step. In this paper, we make significant improvements on both of the two steps. For region proposal we propose a novel lightweight cascade structure which can effectively improve RPN proposal quality. For object recognition we re-implement global context modeling with a few modications and obtain a performance boost (4.2% mAP gain on the ILSVRC 2016 validation set). Besides, we apply the idea of pre-training extensively and show its importance in both steps. Together with common training and test"},"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":"1710.10749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-30T03:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"613d93b1fe15f180f9d3f45e6a7cbd40e2885266b193fe4ac62e61a7e2093300","abstract_canon_sha256":"2b056e4a1041e8fd715177b4b32fd890f410dbfcfbb114f458a62e4e4f435c41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:46.602002Z","signature_b64":"KB5JbZ9w0tmxdLGw+t2WNJofx2NA9zkse+y9Ukr87R5ZmC3ok/XFBRg74e+d3Fa4dfjaeKHCCuZSjcOySMstDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"265b543428e06ab4ce23bfb2019155aebd0fdd389ac514a98089aa981b2f75db","last_reissued_at":"2026-05-18T00:31:46.601399Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:46.601399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cascade Region Proposal and Global Context for Deep Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Li, Di Xie, Qiaoyong Zhong, Shicai Yang, Shiliang Pu, Yingying Zhang","submitted_at":"2017-10-30T03:00:04Z","abstract_excerpt":"Deep region-based object detector consists of a region proposal step and a deep object recognition step. In this paper, we make significant improvements on both of the two steps. For region proposal we propose a novel lightweight cascade structure which can effectively improve RPN proposal quality. For object recognition we re-implement global context modeling with a few modications and obtain a performance boost (4.2% mAP gain on the ILSVRC 2016 validation set). Besides, we apply the idea of pre-training extensively and show its importance in both steps. Together with common training and test"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10749","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":"1710.10749","created_at":"2026-05-18T00:31:46.601493+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10749v1","created_at":"2026-05-18T00:31:46.601493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10749","created_at":"2026-05-18T00:31:46.601493+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZNVINBI4BVL","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZNVINBI4BVLJTRD","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZNVINBI","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.06881","citing_title":"Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11914","citing_title":"Rethinking Classification and Localization for Cascade R-CNN","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZNVINBI4BVLJTRDX6ZADEKVV2","json":"https://pith.science/pith/EZNVINBI4BVLJTRDX6ZADEKVV2.json","graph_json":"https://pith.science/api/pith-number/EZNVINBI4BVLJTRDX6ZADEKVV2/graph.json","events_json":"https://pith.science/api/pith-number/EZNVINBI4BVLJTRDX6ZADEKVV2/events.json","paper":"https://pith.science/paper/EZNVINBI"},"agent_actions":{"view_html":"https://pith.science/pith/EZNVINBI4BVLJTRDX6ZADEKVV2","download_json":"https://pith.science/pith/EZNVINBI4BVLJTRDX6ZADEKVV2.json","view_paper":"https://pith.science/paper/EZNVINBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10749&json=true","fetch_graph":"https://pith.science/api/pith-number/EZNVINBI4BVLJTRDX6ZADEKVV2/graph.json","fetch_events":"https://pith.science/api/pith-number/EZNVINBI4BVLJTRDX6ZADEKVV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZNVINBI4BVLJTRDX6ZADEKVV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZNVINBI4BVLJTRDX6ZADEKVV2/action/storage_attestation","attest_author":"https://pith.science/pith/EZNVINBI4BVLJTRDX6ZADEKVV2/action/author_attestation","sign_citation":"https://pith.science/pith/EZNVINBI4BVLJTRDX6ZADEKVV2/action/citation_signature","submit_replication":"https://pith.science/pith/EZNVINBI4BVLJTRDX6ZADEKVV2/action/replication_record"}},"created_at":"2026-05-18T00:31:46.601493+00:00","updated_at":"2026-05-18T00:31:46.601493+00:00"}