{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L6OSFBLKJQIW5Z7EYDKVIUIYYR","short_pith_number":"pith:L6OSFBLK","schema_version":"1.0","canonical_sha256":"5f9d22856a4c116ee7e4c0d5545118c44d01b7e66b8730cdf52966fe585cf0a3","source":{"kind":"arxiv","id":"2405.19682","version":1},"attestation_state":"computed","paper":{"title":"Fully Test-Time Adaptation for Monocular 3D Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongbin Lin, Shuaicheng Niu, Shuguang Cui, Yifan Zhang, Zhen Li","submitted_at":"2024-05-30T04:37:57Z","abstract_excerpt":"Monocular 3D object detection (Mono 3Det) aims to identify 3D objects from a single RGB image. However, existing methods often assume training and test data follow the same distribution, which may not hold in real-world test scenarios. To address the out-of-distribution (OOD) problems, we explore a new adaptation paradigm for Mono 3Det, termed Fully Test-time Adaptation. It aims to adapt a well-trained model to unlabeled test data by handling potential data distribution shifts at test time without access to training data and test labels. However, applying this paradigm in Mono 3Det poses signi"},"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":"2405.19682","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T04:37:57Z","cross_cats_sorted":[],"title_canon_sha256":"86f37722c454cbcd8f44ccece1c0fa1ddd87d8dc3b242f8ff65ba420c69f977e","abstract_canon_sha256":"ffd6da78519cd49848fc98c20fc50637220e79bbd6f46361933f7e7ae34cb83e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:11.113065Z","signature_b64":"1ckJEbau+63g7OGhtiMXhSOWGHKe+F6AE8B09PYKNozSJADC/ZCLge9aS6EbbPKg483MLpgm39lRUVILgMlcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f9d22856a4c116ee7e4c0d5545118c44d01b7e66b8730cdf52966fe585cf0a3","last_reissued_at":"2026-07-05T08:25:11.112651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:11.112651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Test-Time Adaptation for Monocular 3D Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongbin Lin, Shuaicheng Niu, Shuguang Cui, Yifan Zhang, Zhen Li","submitted_at":"2024-05-30T04:37:57Z","abstract_excerpt":"Monocular 3D object detection (Mono 3Det) aims to identify 3D objects from a single RGB image. However, existing methods often assume training and test data follow the same distribution, which may not hold in real-world test scenarios. To address the out-of-distribution (OOD) problems, we explore a new adaptation paradigm for Mono 3Det, termed Fully Test-time Adaptation. It aims to adapt a well-trained model to unlabeled test data by handling potential data distribution shifts at test time without access to training data and test labels. However, applying this paradigm in Mono 3Det poses signi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19682","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/2405.19682/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":"2405.19682","created_at":"2026-07-05T08:25:11.112709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19682v1","created_at":"2026-07-05T08:25:11.112709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19682","created_at":"2026-07-05T08:25:11.112709+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6OSFBLKJQIW","created_at":"2026-07-05T08:25:11.112709+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6OSFBLKJQIW5Z7E","created_at":"2026-07-05T08:25:11.112709+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6OSFBLK","created_at":"2026-07-05T08:25:11.112709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18860","citing_title":"Improving Batch Normalization with TTA for Robust Object Detection in Self-Driving","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6OSFBLKJQIW5Z7EYDKVIUIYYR","json":"https://pith.science/pith/L6OSFBLKJQIW5Z7EYDKVIUIYYR.json","graph_json":"https://pith.science/api/pith-number/L6OSFBLKJQIW5Z7EYDKVIUIYYR/graph.json","events_json":"https://pith.science/api/pith-number/L6OSFBLKJQIW5Z7EYDKVIUIYYR/events.json","paper":"https://pith.science/paper/L6OSFBLK"},"agent_actions":{"view_html":"https://pith.science/pith/L6OSFBLKJQIW5Z7EYDKVIUIYYR","download_json":"https://pith.science/pith/L6OSFBLKJQIW5Z7EYDKVIUIYYR.json","view_paper":"https://pith.science/paper/L6OSFBLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19682&json=true","fetch_graph":"https://pith.science/api/pith-number/L6OSFBLKJQIW5Z7EYDKVIUIYYR/graph.json","fetch_events":"https://pith.science/api/pith-number/L6OSFBLKJQIW5Z7EYDKVIUIYYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6OSFBLKJQIW5Z7EYDKVIUIYYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6OSFBLKJQIW5Z7EYDKVIUIYYR/action/storage_attestation","attest_author":"https://pith.science/pith/L6OSFBLKJQIW5Z7EYDKVIUIYYR/action/author_attestation","sign_citation":"https://pith.science/pith/L6OSFBLKJQIW5Z7EYDKVIUIYYR/action/citation_signature","submit_replication":"https://pith.science/pith/L6OSFBLKJQIW5Z7EYDKVIUIYYR/action/replication_record"}},"created_at":"2026-07-05T08:25:11.112709+00:00","updated_at":"2026-07-05T08:25:11.112709+00:00"}