{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FPZSVKRY4A4IO6ND3G3KEIOOHD","short_pith_number":"pith:FPZSVKRY","schema_version":"1.0","canonical_sha256":"2bf32aaa38e0388779a3d9b6a221ce38c0ca8ad6b4976588c8fccc78addbce1e","source":{"kind":"arxiv","id":"2006.08547","version":1},"attestation_state":"computed","paper":{"title":"Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","eess.IV"],"primary_cat":"cs.CV","authors_text":"Joachim Denzler, Niklas Hanselmann, Nils G\\\"ahlert, Uwe Franke","submitted_at":"2020-06-15T17:03:23Z","abstract_excerpt":"Object detection is an important task in environment perception for autonomous driving. Modern 2D object detection frameworks such as Yolo, SSD or Faster R-CNN predict multiple bounding boxes per object that are refined using Non-Maximum-Suppression (NMS) to suppress all but one bounding box. While object detection itself is fully end-to-end learnable and does not require any manual parameter selection, standard NMS is parametrized by an overlap threshold that has to be chosen by hand. In practice, this often leads to an inability of standard NMS strategies to distinguish different objects in "},"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":"2006.08547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-15T17:03:23Z","cross_cats_sorted":["cs.LG","cs.RO","eess.IV"],"title_canon_sha256":"31c5347d919e84df20b1a6a6b8c279bd83260538d6717d1fbc0649717e285225","abstract_canon_sha256":"daa996b255415c62e3771e65b5c814f49175e00cf7a17bd0c1acfc9dabc213f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:22.544037Z","signature_b64":"UvusBBCUiy8JnW5GRFNtlGHM8Zw/Xa8GwRLCRXKvG4xMR+ggRqNc8wJgdv4j3Ce7++Eh7RviW786Q1gpMuR5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bf32aaa38e0388779a3d9b6a221ce38c0ca8ad6b4976588c8fccc78addbce1e","last_reissued_at":"2026-07-05T01:10:22.543570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:22.543570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","eess.IV"],"primary_cat":"cs.CV","authors_text":"Joachim Denzler, Niklas Hanselmann, Nils G\\\"ahlert, Uwe Franke","submitted_at":"2020-06-15T17:03:23Z","abstract_excerpt":"Object detection is an important task in environment perception for autonomous driving. Modern 2D object detection frameworks such as Yolo, SSD or Faster R-CNN predict multiple bounding boxes per object that are refined using Non-Maximum-Suppression (NMS) to suppress all but one bounding box. While object detection itself is fully end-to-end learnable and does not require any manual parameter selection, standard NMS is parametrized by an overlap threshold that has to be chosen by hand. In practice, this often leads to an inability of standard NMS strategies to distinguish different objects in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08547","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.08547/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":"2006.08547","created_at":"2026-07-05T01:10:22.543620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.08547v1","created_at":"2026-07-05T01:10:22.543620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08547","created_at":"2026-07-05T01:10:22.543620+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPZSVKRY4A4I","created_at":"2026-07-05T01:10:22.543620+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPZSVKRY4A4IO6ND","created_at":"2026-07-05T01:10:22.543620+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPZSVKRY","created_at":"2026-07-05T01:10:22.543620+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03568","citing_title":"Learned Non-Maximum Suppression for 3D Object Detection","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPZSVKRY4A4IO6ND3G3KEIOOHD","json":"https://pith.science/pith/FPZSVKRY4A4IO6ND3G3KEIOOHD.json","graph_json":"https://pith.science/api/pith-number/FPZSVKRY4A4IO6ND3G3KEIOOHD/graph.json","events_json":"https://pith.science/api/pith-number/FPZSVKRY4A4IO6ND3G3KEIOOHD/events.json","paper":"https://pith.science/paper/FPZSVKRY"},"agent_actions":{"view_html":"https://pith.science/pith/FPZSVKRY4A4IO6ND3G3KEIOOHD","download_json":"https://pith.science/pith/FPZSVKRY4A4IO6ND3G3KEIOOHD.json","view_paper":"https://pith.science/paper/FPZSVKRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.08547&json=true","fetch_graph":"https://pith.science/api/pith-number/FPZSVKRY4A4IO6ND3G3KEIOOHD/graph.json","fetch_events":"https://pith.science/api/pith-number/FPZSVKRY4A4IO6ND3G3KEIOOHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPZSVKRY4A4IO6ND3G3KEIOOHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPZSVKRY4A4IO6ND3G3KEIOOHD/action/storage_attestation","attest_author":"https://pith.science/pith/FPZSVKRY4A4IO6ND3G3KEIOOHD/action/author_attestation","sign_citation":"https://pith.science/pith/FPZSVKRY4A4IO6ND3G3KEIOOHD/action/citation_signature","submit_replication":"https://pith.science/pith/FPZSVKRY4A4IO6ND3G3KEIOOHD/action/replication_record"}},"created_at":"2026-07-05T01:10:22.543620+00:00","updated_at":"2026-07-05T01:10:22.543620+00:00"}