{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VQYBXGT4LJEIAD7A5YWJHTW63Z","short_pith_number":"pith:VQYBXGT4","schema_version":"1.0","canonical_sha256":"ac301b9a7c5a48800fe0ee2c93cedede6d43026ffcdb37e5269db8dd523b42d3","source":{"kind":"arxiv","id":"2005.03572","version":4},"attestation_state":"computed","paper":{"title":"Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongwei Ren, Ping Wang, Qinghua Hu, Rongguang Ye, Wangmeng Zuo, Wei Liu, Zhaohui Zheng","submitted_at":"2020-05-07T16:00:27Z","abstract_excerpt":"Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency. In particular, we consider three geometric factors, i.e., overlap area, normalized central point distance and aspect ratio, which are crucial for measuring bounding box regression in object detection and instan"},"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":"2005.03572","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-07T16:00:27Z","cross_cats_sorted":[],"title_canon_sha256":"cf8d35ac532b88b88ce5811555dc1e4302ee23236185dd110664d96530ff22bc","abstract_canon_sha256":"95519b78585f48fee69d9fe9efca4d4932d2eae3897c38cba788198f842cdbe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:50.072674Z","signature_b64":"Bc/ChJihCjI4Rxz+T+FPZhKn2wHbe3e6fog1CURRuDh2qWNJ08IyzqCWhEY53Qnr5Ljcw1BfxngMoxtq/cO/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac301b9a7c5a48800fe0ee2c93cedede6d43026ffcdb37e5269db8dd523b42d3","last_reissued_at":"2026-07-05T02:54:50.072127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:50.072127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongwei Ren, Ping Wang, Qinghua Hu, Rongguang Ye, Wangmeng Zuo, Wei Liu, Zhaohui Zheng","submitted_at":"2020-05-07T16:00:27Z","abstract_excerpt":"Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency. In particular, we consider three geometric factors, i.e., overlap area, normalized central point distance and aspect ratio, which are crucial for measuring bounding box regression in object detection and instan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03572","kind":"arxiv","version":4},"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/2005.03572/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":"2005.03572","created_at":"2026-07-05T02:54:50.072178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.03572v4","created_at":"2026-07-05T02:54:50.072178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03572","created_at":"2026-07-05T02:54:50.072178+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQYBXGT4LJEI","created_at":"2026-07-05T02:54:50.072178+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQYBXGT4LJEIAD7A","created_at":"2026-07-05T02:54:50.072178+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQYBXGT4","created_at":"2026-07-05T02:54:50.072178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00844","citing_title":"MoEIoU: Rethinking Bounding-Box Regression as a Mixture of Experts","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQYBXGT4LJEIAD7A5YWJHTW63Z","json":"https://pith.science/pith/VQYBXGT4LJEIAD7A5YWJHTW63Z.json","graph_json":"https://pith.science/api/pith-number/VQYBXGT4LJEIAD7A5YWJHTW63Z/graph.json","events_json":"https://pith.science/api/pith-number/VQYBXGT4LJEIAD7A5YWJHTW63Z/events.json","paper":"https://pith.science/paper/VQYBXGT4"},"agent_actions":{"view_html":"https://pith.science/pith/VQYBXGT4LJEIAD7A5YWJHTW63Z","download_json":"https://pith.science/pith/VQYBXGT4LJEIAD7A5YWJHTW63Z.json","view_paper":"https://pith.science/paper/VQYBXGT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.03572&json=true","fetch_graph":"https://pith.science/api/pith-number/VQYBXGT4LJEIAD7A5YWJHTW63Z/graph.json","fetch_events":"https://pith.science/api/pith-number/VQYBXGT4LJEIAD7A5YWJHTW63Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQYBXGT4LJEIAD7A5YWJHTW63Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQYBXGT4LJEIAD7A5YWJHTW63Z/action/storage_attestation","attest_author":"https://pith.science/pith/VQYBXGT4LJEIAD7A5YWJHTW63Z/action/author_attestation","sign_citation":"https://pith.science/pith/VQYBXGT4LJEIAD7A5YWJHTW63Z/action/citation_signature","submit_replication":"https://pith.science/pith/VQYBXGT4LJEIAD7A5YWJHTW63Z/action/replication_record"}},"created_at":"2026-07-05T02:54:50.072178+00:00","updated_at":"2026-07-05T02:54:50.072178+00:00"}