{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MKIQWSGMFEVNZLUUUPUK7PS5US","short_pith_number":"pith:MKIQWSGM","schema_version":"1.0","canonical_sha256":"62910b48cc292adcae94a3e8afbe5da4b88ea094db0ba738739ccbb4ee2e9abb","source":{"kind":"arxiv","id":"2106.06072","version":1},"attestation_state":"computed","paper":{"title":"Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Claudio Jung, Jeffri M. Llerena, Lucas N. Kristen, Luis Felipe Zeni","submitted_at":"2021-06-10T22:24:31Z","abstract_excerpt":"Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a fuzzy representation of object regions using Gaussian distributions, which provides an implicit binary representation as (potentially rotated) ellipses. We also present a similarity measure for the Gaussian distributions based on the Hellinger Distance, which can be viewed as a Probabilistic Intersection-over-Union (ProbIoU). Our experimental results show that the proposed Gaussian representations are closer to annotated segmentation masks in publicly available dat"},"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":"2106.06072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-10T22:24:31Z","cross_cats_sorted":[],"title_canon_sha256":"bc02612b553eeda497adcb61fcb1c42e9be007c3258a6b5809f3309cbe86defe","abstract_canon_sha256":"54692a3b58070f3f5a11940390b9311c6e61ee98828c2f081dbbd13a11f29573"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:29.375936Z","signature_b64":"8KZY2+n8lbsTUSKefa7CgsmTvJoppPLhDmnRy0t4wfrbvuRKsHPCcdK5m8KcZDOq0W/67FUtPaxxRpXAq7kdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62910b48cc292adcae94a3e8afbe5da4b88ea094db0ba738739ccbb4ee2e9abb","last_reissued_at":"2026-07-05T08:00:29.375449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:29.375449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Claudio Jung, Jeffri M. Llerena, Lucas N. Kristen, Luis Felipe Zeni","submitted_at":"2021-06-10T22:24:31Z","abstract_excerpt":"Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a fuzzy representation of object regions using Gaussian distributions, which provides an implicit binary representation as (potentially rotated) ellipses. We also present a similarity measure for the Gaussian distributions based on the Hellinger Distance, which can be viewed as a Probabilistic Intersection-over-Union (ProbIoU). Our experimental results show that the proposed Gaussian representations are closer to annotated segmentation masks in publicly available dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06072","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/2106.06072/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":"2106.06072","created_at":"2026-07-05T08:00:29.375505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06072v1","created_at":"2026-07-05T08:00:29.375505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06072","created_at":"2026-07-05T08:00:29.375505+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKIQWSGMFEVN","created_at":"2026-07-05T08:00:29.375505+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKIQWSGMFEVNZLUU","created_at":"2026-07-05T08:00:29.375505+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKIQWSGM","created_at":"2026-07-05T08:00:29.375505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03748","citing_title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKIQWSGMFEVNZLUUUPUK7PS5US","json":"https://pith.science/pith/MKIQWSGMFEVNZLUUUPUK7PS5US.json","graph_json":"https://pith.science/api/pith-number/MKIQWSGMFEVNZLUUUPUK7PS5US/graph.json","events_json":"https://pith.science/api/pith-number/MKIQWSGMFEVNZLUUUPUK7PS5US/events.json","paper":"https://pith.science/paper/MKIQWSGM"},"agent_actions":{"view_html":"https://pith.science/pith/MKIQWSGMFEVNZLUUUPUK7PS5US","download_json":"https://pith.science/pith/MKIQWSGMFEVNZLUUUPUK7PS5US.json","view_paper":"https://pith.science/paper/MKIQWSGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06072&json=true","fetch_graph":"https://pith.science/api/pith-number/MKIQWSGMFEVNZLUUUPUK7PS5US/graph.json","fetch_events":"https://pith.science/api/pith-number/MKIQWSGMFEVNZLUUUPUK7PS5US/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKIQWSGMFEVNZLUUUPUK7PS5US/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKIQWSGMFEVNZLUUUPUK7PS5US/action/storage_attestation","attest_author":"https://pith.science/pith/MKIQWSGMFEVNZLUUUPUK7PS5US/action/author_attestation","sign_citation":"https://pith.science/pith/MKIQWSGMFEVNZLUUUPUK7PS5US/action/citation_signature","submit_replication":"https://pith.science/pith/MKIQWSGMFEVNZLUUUPUK7PS5US/action/replication_record"}},"created_at":"2026-07-05T08:00:29.375505+00:00","updated_at":"2026-07-05T08:00:29.375505+00:00"}