{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5E7YJCKXHS2GLL3E5IKSPPWEK7","short_pith_number":"pith:5E7YJCKX","schema_version":"1.0","canonical_sha256":"e93f8489573cb465af64ea1527bec457c9a138743d56493b2a636b270f5b3258","source":{"kind":"arxiv","id":"2403.07222","version":2},"attestation_state":"computed","paper":{"title":"You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aneeshan Sain, Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Subhadeep Koley, Tao Xiang, Yi-Zhe Song","submitted_at":"2024-03-12T00:27:18Z","abstract_excerpt":"Two primary input modalities prevail in image retrieval: sketch and text. While text is widely used for inter-category retrieval tasks, sketches have been established as the sole preferred modality for fine-grained image retrieval due to their ability to capture intricate visual details. In this paper, we question the reliance on sketches alone for fine-grained image retrieval by simultaneously exploring the fine-grained representation capabilities of both sketch and text, orchestrating a duet between the two. The end result enables precise retrievals previously unattainable, allowing users to"},"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":"2403.07222","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T00:27:18Z","cross_cats_sorted":[],"title_canon_sha256":"247f3834295adcf4386b6294b845a2519a3a10300ef89a908dd7c0f4a96c1ee7","abstract_canon_sha256":"be2cd20d959b9c3e7aa31b00b1530397cb27f4189c55d1d101ed954efa528fcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:49.472871Z","signature_b64":"j1pO/YcTawnjdF/NcphGL2LymJ8p1nSAxwWJI5xfIgIwXfN1V7wrgwyVJD4i2eO3dKv73WFYF5XzG8O6/lFRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e93f8489573cb465af64ea1527bec457c9a138743d56493b2a636b270f5b3258","last_reissued_at":"2026-07-05T07:58:49.472427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:49.472427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aneeshan Sain, Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Subhadeep Koley, Tao Xiang, Yi-Zhe Song","submitted_at":"2024-03-12T00:27:18Z","abstract_excerpt":"Two primary input modalities prevail in image retrieval: sketch and text. While text is widely used for inter-category retrieval tasks, sketches have been established as the sole preferred modality for fine-grained image retrieval due to their ability to capture intricate visual details. In this paper, we question the reliance on sketches alone for fine-grained image retrieval by simultaneously exploring the fine-grained representation capabilities of both sketch and text, orchestrating a duet between the two. The end result enables precise retrievals previously unattainable, allowing users to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07222","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/2403.07222/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":"2403.07222","created_at":"2026-07-05T07:58:49.472482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07222v2","created_at":"2026-07-05T07:58:49.472482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07222","created_at":"2026-07-05T07:58:49.472482+00:00"},{"alias_kind":"pith_short_12","alias_value":"5E7YJCKXHS2G","created_at":"2026-07-05T07:58:49.472482+00:00"},{"alias_kind":"pith_short_16","alias_value":"5E7YJCKXHS2GLL3E","created_at":"2026-07-05T07:58:49.472482+00:00"},{"alias_kind":"pith_short_8","alias_value":"5E7YJCKX","created_at":"2026-07-05T07:58:49.472482+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/5E7YJCKXHS2GLL3E5IKSPPWEK7","json":"https://pith.science/pith/5E7YJCKXHS2GLL3E5IKSPPWEK7.json","graph_json":"https://pith.science/api/pith-number/5E7YJCKXHS2GLL3E5IKSPPWEK7/graph.json","events_json":"https://pith.science/api/pith-number/5E7YJCKXHS2GLL3E5IKSPPWEK7/events.json","paper":"https://pith.science/paper/5E7YJCKX"},"agent_actions":{"view_html":"https://pith.science/pith/5E7YJCKXHS2GLL3E5IKSPPWEK7","download_json":"https://pith.science/pith/5E7YJCKXHS2GLL3E5IKSPPWEK7.json","view_paper":"https://pith.science/paper/5E7YJCKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07222&json=true","fetch_graph":"https://pith.science/api/pith-number/5E7YJCKXHS2GLL3E5IKSPPWEK7/graph.json","fetch_events":"https://pith.science/api/pith-number/5E7YJCKXHS2GLL3E5IKSPPWEK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5E7YJCKXHS2GLL3E5IKSPPWEK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5E7YJCKXHS2GLL3E5IKSPPWEK7/action/storage_attestation","attest_author":"https://pith.science/pith/5E7YJCKXHS2GLL3E5IKSPPWEK7/action/author_attestation","sign_citation":"https://pith.science/pith/5E7YJCKXHS2GLL3E5IKSPPWEK7/action/citation_signature","submit_replication":"https://pith.science/pith/5E7YJCKXHS2GLL3E5IKSPPWEK7/action/replication_record"}},"created_at":"2026-07-05T07:58:49.472482+00:00","updated_at":"2026-07-05T07:58:49.472482+00:00"}