{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OYBF5OTS6QTGEXWIQZWGLO7PMD","short_pith_number":"pith:OYBF5OTS","schema_version":"1.0","canonical_sha256":"76025eba72f426625ec8866c65bbef60d17711b3209f1082d117e328e6dc4c0c","source":{"kind":"arxiv","id":"2406.11820","version":1},"attestation_state":"computed","paper":{"title":"Composing Object Relations and Attributes for Image-Text Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Chuong Huynh, Khoi Pham, Ser-Nam Lim","submitted_at":"2024-06-17T17:56:01Z","abstract_excerpt":"We study the visual semantic embedding problem for image-text matching. Most existing work utilizes a tailored cross-attention mechanism to perform local alignment across the two image and text modalities. This is computationally expensive, even though it is more powerful than the unimodal dual-encoder approach. This work introduces a dual-encoder image-text matching model, leveraging a scene graph to represent captions with nodes for objects and attributes interconnected by relational edges. Utilizing a graph attention network, our model efficiently encodes object-attribute and object-object "},"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":"2406.11820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"6fb5a15b2cd77be5a14c88c2a75a27dac281fb0a3c0b10760feea23bfd7ab4b6","abstract_canon_sha256":"4026ebb22e2c819f316002bc8d4ba914802d24c1f29064007e2323095515c144"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:58.301284Z","signature_b64":"bgBqEvgK/IdQdYCPksHoPoTEaIAu6OTGhj3z3fKhl3kUoyX0MDuxNtyCDCM5UMpqlVOx9Z/gJewmuwoFHJmQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76025eba72f426625ec8866c65bbef60d17711b3209f1082d117e328e6dc4c0c","last_reissued_at":"2026-07-05T08:32:58.300870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:58.300870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Composing Object Relations and Attributes for Image-Text Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Chuong Huynh, Khoi Pham, Ser-Nam Lim","submitted_at":"2024-06-17T17:56:01Z","abstract_excerpt":"We study the visual semantic embedding problem for image-text matching. Most existing work utilizes a tailored cross-attention mechanism to perform local alignment across the two image and text modalities. This is computationally expensive, even though it is more powerful than the unimodal dual-encoder approach. This work introduces a dual-encoder image-text matching model, leveraging a scene graph to represent captions with nodes for objects and attributes interconnected by relational edges. Utilizing a graph attention network, our model efficiently encodes object-attribute and object-object "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11820","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/2406.11820/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":"2406.11820","created_at":"2026-07-05T08:32:58.300924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11820v1","created_at":"2026-07-05T08:32:58.300924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11820","created_at":"2026-07-05T08:32:58.300924+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYBF5OTS6QTG","created_at":"2026-07-05T08:32:58.300924+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYBF5OTS6QTGEXWI","created_at":"2026-07-05T08:32:58.300924+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYBF5OTS","created_at":"2026-07-05T08:32:58.300924+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/OYBF5OTS6QTGEXWIQZWGLO7PMD","json":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD.json","graph_json":"https://pith.science/api/pith-number/OYBF5OTS6QTGEXWIQZWGLO7PMD/graph.json","events_json":"https://pith.science/api/pith-number/OYBF5OTS6QTGEXWIQZWGLO7PMD/events.json","paper":"https://pith.science/paper/OYBF5OTS"},"agent_actions":{"view_html":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD","download_json":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD.json","view_paper":"https://pith.science/paper/OYBF5OTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11820&json=true","fetch_graph":"https://pith.science/api/pith-number/OYBF5OTS6QTGEXWIQZWGLO7PMD/graph.json","fetch_events":"https://pith.science/api/pith-number/OYBF5OTS6QTGEXWIQZWGLO7PMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/action/storage_attestation","attest_author":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/action/author_attestation","sign_citation":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/action/citation_signature","submit_replication":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/action/replication_record"}},"created_at":"2026-07-05T08:32:58.300924+00:00","updated_at":"2026-07-05T08:32:58.300924+00:00"}