{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5RCOJWSHZASQJWOQOBWBRQHENY","short_pith_number":"pith:5RCOJWSH","schema_version":"1.0","canonical_sha256":"ec44e4da47c82504d9d0706c18c0e46e2351c8c7716a5c86e41144d4faea762d","source":{"kind":"arxiv","id":"2502.14195","version":2},"attestation_state":"computed","paper":{"title":"Bridging Text and Vision: A Multi-View Text-Vision Registration Approach for Cross-Modal Place Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Gang Chen, Jinwei Qiao, Pengjie Xu, Tianyi Shang, Weijun Hu, Zhenyu Li, Zihan Ruan","submitted_at":"2025-02-20T02:00:02Z","abstract_excerpt":"Mobile robots necessitate advanced natural language understanding capabilities to accurately identify locations and perform tasks such as package delivery. However, traditional visual place recognition (VPR) methods rely solely on single-view visual information and cannot interpret human language descriptions. To overcome this challenge, we bridge text and vision by proposing a multiview (360{\\deg} views of the surroundings) text-vision registration approach called Text4VPR for place recognition task, which is the first method that exclusively utilizes textual descriptions to match a database "},"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":"2502.14195","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T02:00:02Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1c9cbad926d2b3a4ad208483a4798f78f9d8038700f0bc9bc546a5fcbe7347be","abstract_canon_sha256":"77b53955ceba0594fb8d1b78751272d5728a63e03fff2bee1af8c67c37ee0148"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:14.379454Z","signature_b64":"x98ZYpaNwa1aMHd7unL0+bVhHZlBdvwYaSM1msZ9jw9OvD1Yjm6XMq5rGL9Mec1obLmjkjpc+H/db1uSxz24AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec44e4da47c82504d9d0706c18c0e46e2351c8c7716a5c86e41144d4faea762d","last_reissued_at":"2026-07-05T10:26:14.378524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:14.378524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Text and Vision: A Multi-View Text-Vision Registration Approach for Cross-Modal Place Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Gang Chen, Jinwei Qiao, Pengjie Xu, Tianyi Shang, Weijun Hu, Zhenyu Li, Zihan Ruan","submitted_at":"2025-02-20T02:00:02Z","abstract_excerpt":"Mobile robots necessitate advanced natural language understanding capabilities to accurately identify locations and perform tasks such as package delivery. However, traditional visual place recognition (VPR) methods rely solely on single-view visual information and cannot interpret human language descriptions. To overcome this challenge, we bridge text and vision by proposing a multiview (360{\\deg} views of the surroundings) text-vision registration approach called Text4VPR for place recognition task, which is the first method that exclusively utilizes textual descriptions to match a database "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14195","kind":"arxiv","version":2},"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/2502.14195/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":"2502.14195","created_at":"2026-07-05T10:26:14.378654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14195v2","created_at":"2026-07-05T10:26:14.378654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14195","created_at":"2026-07-05T10:26:14.378654+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RCOJWSHZASQ","created_at":"2026-07-05T10:26:14.378654+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RCOJWSHZASQJWOQ","created_at":"2026-07-05T10:26:14.378654+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RCOJWSH","created_at":"2026-07-05T10:26:14.378654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RCOJWSHZASQJWOQOBWBRQHENY","json":"https://pith.science/pith/5RCOJWSHZASQJWOQOBWBRQHENY.json","graph_json":"https://pith.science/api/pith-number/5RCOJWSHZASQJWOQOBWBRQHENY/graph.json","events_json":"https://pith.science/api/pith-number/5RCOJWSHZASQJWOQOBWBRQHENY/events.json","paper":"https://pith.science/paper/5RCOJWSH"},"agent_actions":{"view_html":"https://pith.science/pith/5RCOJWSHZASQJWOQOBWBRQHENY","download_json":"https://pith.science/pith/5RCOJWSHZASQJWOQOBWBRQHENY.json","view_paper":"https://pith.science/paper/5RCOJWSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14195&json=true","fetch_graph":"https://pith.science/api/pith-number/5RCOJWSHZASQJWOQOBWBRQHENY/graph.json","fetch_events":"https://pith.science/api/pith-number/5RCOJWSHZASQJWOQOBWBRQHENY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RCOJWSHZASQJWOQOBWBRQHENY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RCOJWSHZASQJWOQOBWBRQHENY/action/storage_attestation","attest_author":"https://pith.science/pith/5RCOJWSHZASQJWOQOBWBRQHENY/action/author_attestation","sign_citation":"https://pith.science/pith/5RCOJWSHZASQJWOQOBWBRQHENY/action/citation_signature","submit_replication":"https://pith.science/pith/5RCOJWSHZASQJWOQOBWBRQHENY/action/replication_record"}},"created_at":"2026-07-05T10:26:14.378654+00:00","updated_at":"2026-07-05T10:26:14.378654+00:00"}