{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AVDJBIQHMTLHH4SQIX35O56PEZ","short_pith_number":"pith:AVDJBIQH","schema_version":"1.0","canonical_sha256":"054690a20764d673f25045f7d777cf265612ce6ebe3f9747e4d91f618fb758fa","source":{"kind":"arxiv","id":"1906.06892","version":1},"attestation_state":"computed","paper":{"title":"ParNet: Position-aware Aggregated Relation Network for Image-Text matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Lun Huang, Wenmin Wang, Xiaoyong Wei, Yaxian Xia","submitted_at":"2019-06-17T08:26:43Z","abstract_excerpt":"Exploring fine-grained relationship between entities(e.g. objects in image or words in sentence) has great contribution to understand multimedia content precisely. Previous attention mechanism employed in image-text matching either takes multiple self attention steps to gather correspondences or uses image objects (or words) as context to infer image-text similarity. However, they only take advantage of semantic information without considering that objects' relative position also contributes to image understanding. To this end, we introduce a novel position-aware relation module to model both "},"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":"1906.06892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-17T08:26:43Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"d908ee43667c1116c177b7a0780d4f035c7cbbc907e8c8bb4e6d68c6755e44e6","abstract_canon_sha256":"6b401b5b2922d97157e18638e4c32485c2bc42b6dc8d177246266da4e960c5ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:12.414719Z","signature_b64":"CQJXalOi7T8Gs23o/29xHdps6XzcmbOiRbFlprAnajc55LOD3cdHxSXBTXv/7o28PzQRp3lLa/5UHble8rdmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"054690a20764d673f25045f7d777cf265612ce6ebe3f9747e4d91f618fb758fa","last_reissued_at":"2026-05-17T23:43:12.414214Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:12.414214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParNet: Position-aware Aggregated Relation Network for Image-Text matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Lun Huang, Wenmin Wang, Xiaoyong Wei, Yaxian Xia","submitted_at":"2019-06-17T08:26:43Z","abstract_excerpt":"Exploring fine-grained relationship between entities(e.g. objects in image or words in sentence) has great contribution to understand multimedia content precisely. Previous attention mechanism employed in image-text matching either takes multiple self attention steps to gather correspondences or uses image objects (or words) as context to infer image-text similarity. However, they only take advantage of semantic information without considering that objects' relative position also contributes to image understanding. To this end, we introduce a novel position-aware relation module to model both "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06892","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":""},"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":"1906.06892","created_at":"2026-05-17T23:43:12.414305+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.06892v1","created_at":"2026-05-17T23:43:12.414305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06892","created_at":"2026-05-17T23:43:12.414305+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVDJBIQHMTLH","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVDJBIQHMTLHH4SQ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVDJBIQH","created_at":"2026-05-18T12:33:12.712433+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/AVDJBIQHMTLHH4SQIX35O56PEZ","json":"https://pith.science/pith/AVDJBIQHMTLHH4SQIX35O56PEZ.json","graph_json":"https://pith.science/api/pith-number/AVDJBIQHMTLHH4SQIX35O56PEZ/graph.json","events_json":"https://pith.science/api/pith-number/AVDJBIQHMTLHH4SQIX35O56PEZ/events.json","paper":"https://pith.science/paper/AVDJBIQH"},"agent_actions":{"view_html":"https://pith.science/pith/AVDJBIQHMTLHH4SQIX35O56PEZ","download_json":"https://pith.science/pith/AVDJBIQHMTLHH4SQIX35O56PEZ.json","view_paper":"https://pith.science/paper/AVDJBIQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.06892&json=true","fetch_graph":"https://pith.science/api/pith-number/AVDJBIQHMTLHH4SQIX35O56PEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/AVDJBIQHMTLHH4SQIX35O56PEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVDJBIQHMTLHH4SQIX35O56PEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVDJBIQHMTLHH4SQIX35O56PEZ/action/storage_attestation","attest_author":"https://pith.science/pith/AVDJBIQHMTLHH4SQIX35O56PEZ/action/author_attestation","sign_citation":"https://pith.science/pith/AVDJBIQHMTLHH4SQIX35O56PEZ/action/citation_signature","submit_replication":"https://pith.science/pith/AVDJBIQHMTLHH4SQIX35O56PEZ/action/replication_record"}},"created_at":"2026-05-17T23:43:12.414305+00:00","updated_at":"2026-05-17T23:43:12.414305+00:00"}