{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OYO4JHOVXFIY34656SRNHZWC5D","short_pith_number":"pith:OYO4JHOV","schema_version":"1.0","canonical_sha256":"761dc49dd5b9518df3ddf4a2d3e6c2e8f10d25419a8b7be49e0c877631997c3a","source":{"kind":"arxiv","id":"2401.09725","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Image-Text Matching with Adaptive Feature Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"I.V. Ramakrishnan, Yunting Yin, Zuhui Wang","submitted_at":"2024-01-18T05:00:18Z","abstract_excerpt":"Image-text matching aims to find matched cross-modal pairs accurately. While current methods often rely on projecting cross-modal features into a common embedding space, they frequently suffer from imbalanced feature representations across different modalities, leading to unreliable retrieval results. To address these limitations, we introduce a novel Feature Enhancement Module that adaptively aggregates single-modal features for more balanced and robust image-text retrieval. Additionally, we propose a new loss function that overcomes the shortcomings of original triplet ranking loss, thereby "},"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":"2401.09725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-18T05:00:18Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"285418593a41ef403ebdbbb50e98e7fac2ae15c714226cb65c046768b40b1d1e","abstract_canon_sha256":"76d03b0ac771777e171cf8eb387f183e11600003707d3508bde4d88e3ef6eec7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:01.292685Z","signature_b64":"aSomqL4eUkhmkYtOojHEASi6Jc/9zrSCkTbPVUZQfh+CFWvI0KcZwDMyxxZWoib6+pZhf2c9ftnZpeXijBUcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"761dc49dd5b9518df3ddf4a2d3e6c2e8f10d25419a8b7be49e0c877631997c3a","last_reissued_at":"2026-07-05T07:35:01.292092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:01.292092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Image-Text Matching with Adaptive Feature Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"I.V. Ramakrishnan, Yunting Yin, Zuhui Wang","submitted_at":"2024-01-18T05:00:18Z","abstract_excerpt":"Image-text matching aims to find matched cross-modal pairs accurately. While current methods often rely on projecting cross-modal features into a common embedding space, they frequently suffer from imbalanced feature representations across different modalities, leading to unreliable retrieval results. To address these limitations, we introduce a novel Feature Enhancement Module that adaptively aggregates single-modal features for more balanced and robust image-text retrieval. Additionally, we propose a new loss function that overcomes the shortcomings of original triplet ranking loss, thereby "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09725","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/2401.09725/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":"2401.09725","created_at":"2026-07-05T07:35:01.292173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09725v1","created_at":"2026-07-05T07:35:01.292173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09725","created_at":"2026-07-05T07:35:01.292173+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYO4JHOVXFIY","created_at":"2026-07-05T07:35:01.292173+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYO4JHOVXFIY3465","created_at":"2026-07-05T07:35:01.292173+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYO4JHOV","created_at":"2026-07-05T07:35:01.292173+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/OYO4JHOVXFIY34656SRNHZWC5D","json":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D.json","graph_json":"https://pith.science/api/pith-number/OYO4JHOVXFIY34656SRNHZWC5D/graph.json","events_json":"https://pith.science/api/pith-number/OYO4JHOVXFIY34656SRNHZWC5D/events.json","paper":"https://pith.science/paper/OYO4JHOV"},"agent_actions":{"view_html":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D","download_json":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D.json","view_paper":"https://pith.science/paper/OYO4JHOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09725&json=true","fetch_graph":"https://pith.science/api/pith-number/OYO4JHOVXFIY34656SRNHZWC5D/graph.json","fetch_events":"https://pith.science/api/pith-number/OYO4JHOVXFIY34656SRNHZWC5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D/action/storage_attestation","attest_author":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D/action/author_attestation","sign_citation":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D/action/citation_signature","submit_replication":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D/action/replication_record"}},"created_at":"2026-07-05T07:35:01.292173+00:00","updated_at":"2026-07-05T07:35:01.292173+00:00"}