{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FZKQWJTI7H2FX6TZVAH3GIR3IT","short_pith_number":"pith:FZKQWJTI","schema_version":"1.0","canonical_sha256":"2e550b2668f9f45bfa79a80fb3223b44d7313bcc61774f7c6cc888d238d83ff6","source":{"kind":"arxiv","id":"1901.07702","version":1},"attestation_state":"computed","paper":{"title":"Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmed Taha, Larry Davis, Teruhisa Misu, Xitong Yang, Yi-Ting Chen","submitted_at":"2019-01-23T03:00:24Z","abstract_excerpt":"We cast visual retrieval as a regression problem by posing triplet loss as a regression loss. This enables epistemic uncertainty estimation using dropout as a Bayesian approximation framework in retrieval. Accordingly, Monte Carlo (MC) sampling is leveraged to boost retrieval performance. Our approach is evaluated on two applications: person re-identification and autonomous car driving. Comparable state-of-the-art results are achieved on multiple datasets for the former application.\n  We leverage the Honda driving dataset (HDD) for autonomous car driving application. It provides multiple modal"},"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":"1901.07702","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-23T03:00:24Z","cross_cats_sorted":[],"title_canon_sha256":"1a00e6c57deac832fe60be94df33f57effa85028718ee286b9b995745e3ffc81","abstract_canon_sha256":"258bd786e663f43109a63aded648e8ed77b109337cc31fca843e7ffa990d19d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:41.778854Z","signature_b64":"nUYt3wJtlomo8PSPQaFYp0WlDxuGygTHjjaWj2j3WdZsLTAc9WcvWbSZdEZtdMioW0mZxXtmaNe6bFcxh+rKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e550b2668f9f45bfa79a80fb3223b44d7313bcc61774f7c6cc888d238d83ff6","last_reissued_at":"2026-05-17T23:55:41.778281Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:41.778281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmed Taha, Larry Davis, Teruhisa Misu, Xitong Yang, Yi-Ting Chen","submitted_at":"2019-01-23T03:00:24Z","abstract_excerpt":"We cast visual retrieval as a regression problem by posing triplet loss as a regression loss. This enables epistemic uncertainty estimation using dropout as a Bayesian approximation framework in retrieval. Accordingly, Monte Carlo (MC) sampling is leveraged to boost retrieval performance. Our approach is evaluated on two applications: person re-identification and autonomous car driving. Comparable state-of-the-art results are achieved on multiple datasets for the former application.\n  We leverage the Honda driving dataset (HDD) for autonomous car driving application. It provides multiple modal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07702","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":"1901.07702","created_at":"2026-05-17T23:55:41.778378+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.07702v1","created_at":"2026-05-17T23:55:41.778378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07702","created_at":"2026-05-17T23:55:41.778378+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZKQWJTI7H2F","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZKQWJTI7H2FX6TZ","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZKQWJTI","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZKQWJTI7H2FX6TZVAH3GIR3IT","json":"https://pith.science/pith/FZKQWJTI7H2FX6TZVAH3GIR3IT.json","graph_json":"https://pith.science/api/pith-number/FZKQWJTI7H2FX6TZVAH3GIR3IT/graph.json","events_json":"https://pith.science/api/pith-number/FZKQWJTI7H2FX6TZVAH3GIR3IT/events.json","paper":"https://pith.science/paper/FZKQWJTI"},"agent_actions":{"view_html":"https://pith.science/pith/FZKQWJTI7H2FX6TZVAH3GIR3IT","download_json":"https://pith.science/pith/FZKQWJTI7H2FX6TZVAH3GIR3IT.json","view_paper":"https://pith.science/paper/FZKQWJTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.07702&json=true","fetch_graph":"https://pith.science/api/pith-number/FZKQWJTI7H2FX6TZVAH3GIR3IT/graph.json","fetch_events":"https://pith.science/api/pith-number/FZKQWJTI7H2FX6TZVAH3GIR3IT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZKQWJTI7H2FX6TZVAH3GIR3IT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZKQWJTI7H2FX6TZVAH3GIR3IT/action/storage_attestation","attest_author":"https://pith.science/pith/FZKQWJTI7H2FX6TZVAH3GIR3IT/action/author_attestation","sign_citation":"https://pith.science/pith/FZKQWJTI7H2FX6TZVAH3GIR3IT/action/citation_signature","submit_replication":"https://pith.science/pith/FZKQWJTI7H2FX6TZVAH3GIR3IT/action/replication_record"}},"created_at":"2026-05-17T23:55:41.778378+00:00","updated_at":"2026-05-17T23:55:41.778378+00:00"}