{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SSK7Z4B7SM25GAQQM7E3SUBXEC","short_pith_number":"pith:SSK7Z4B7","schema_version":"1.0","canonical_sha256":"9495fcf03f9335d3021067c9b9503720b20f1bf439914e659f67bfc583e64802","source":{"kind":"arxiv","id":"2101.00265","version":2},"attestation_state":"computed","paper":{"title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kyusong Lee, Tiancheng Zhao, Xiaopeng Lu","submitted_at":"2021-01-01T16:29:17Z","abstract_excerpt":"Text-to-image retrieval is an essential task in cross-modal information retrieval, i.e., retrieving relevant images from a large and unlabelled dataset given textual queries. In this paper, we propose VisualSparta, a novel (Visual-text Sparse Transformer Matching) model that shows significant improvement in terms of both accuracy and efficiency. VisualSparta is capable of outperforming previous state-of-the-art scalable methods in MSCOCO and Flickr30K. We also show that it achieves substantial retrieving speed advantages, i.e., for a 1 million image index, VisualSparta using CPU gets ~391X spe"},"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":"2101.00265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-01T16:29:17Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"34abc4a8470b0f0f9d3696947e3543e7380524f076ef79764fd7876d67f82b2c","abstract_canon_sha256":"2048a9d97adddf40d3b143c173996e9e63bb77bbdfc7384ee43db1997a41fa7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:03.236780Z","signature_b64":"VcyANAPZFXTB/ymkMIH8atjTpw1H/QLD6zK5Qzt6KknDsIEWlwOOplqZtPbCRoIUK4BFXophZXlxcyPedvnmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9495fcf03f9335d3021067c9b9503720b20f1bf439914e659f67bfc583e64802","last_reissued_at":"2026-07-05T02:42:03.236310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:03.236310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kyusong Lee, Tiancheng Zhao, Xiaopeng Lu","submitted_at":"2021-01-01T16:29:17Z","abstract_excerpt":"Text-to-image retrieval is an essential task in cross-modal information retrieval, i.e., retrieving relevant images from a large and unlabelled dataset given textual queries. In this paper, we propose VisualSparta, a novel (Visual-text Sparse Transformer Matching) model that shows significant improvement in terms of both accuracy and efficiency. VisualSparta is capable of outperforming previous state-of-the-art scalable methods in MSCOCO and Flickr30K. We also show that it achieves substantial retrieving speed advantages, i.e., for a 1 million image index, VisualSparta using CPU gets ~391X spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00265","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/2101.00265/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":"2101.00265","created_at":"2026-07-05T02:42:03.236374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.00265v2","created_at":"2026-07-05T02:42:03.236374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00265","created_at":"2026-07-05T02:42:03.236374+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSK7Z4B7SM25","created_at":"2026-07-05T02:42:03.236374+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSK7Z4B7SM25GAQQ","created_at":"2026-07-05T02:42:03.236374+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSK7Z4B7","created_at":"2026-07-05T02:42:03.236374+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/SSK7Z4B7SM25GAQQM7E3SUBXEC","json":"https://pith.science/pith/SSK7Z4B7SM25GAQQM7E3SUBXEC.json","graph_json":"https://pith.science/api/pith-number/SSK7Z4B7SM25GAQQM7E3SUBXEC/graph.json","events_json":"https://pith.science/api/pith-number/SSK7Z4B7SM25GAQQM7E3SUBXEC/events.json","paper":"https://pith.science/paper/SSK7Z4B7"},"agent_actions":{"view_html":"https://pith.science/pith/SSK7Z4B7SM25GAQQM7E3SUBXEC","download_json":"https://pith.science/pith/SSK7Z4B7SM25GAQQM7E3SUBXEC.json","view_paper":"https://pith.science/paper/SSK7Z4B7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.00265&json=true","fetch_graph":"https://pith.science/api/pith-number/SSK7Z4B7SM25GAQQM7E3SUBXEC/graph.json","fetch_events":"https://pith.science/api/pith-number/SSK7Z4B7SM25GAQQM7E3SUBXEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSK7Z4B7SM25GAQQM7E3SUBXEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSK7Z4B7SM25GAQQM7E3SUBXEC/action/storage_attestation","attest_author":"https://pith.science/pith/SSK7Z4B7SM25GAQQM7E3SUBXEC/action/author_attestation","sign_citation":"https://pith.science/pith/SSK7Z4B7SM25GAQQM7E3SUBXEC/action/citation_signature","submit_replication":"https://pith.science/pith/SSK7Z4B7SM25GAQQM7E3SUBXEC/action/replication_record"}},"created_at":"2026-07-05T02:42:03.236374+00:00","updated_at":"2026-07-05T02:42:03.236374+00:00"}