{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JZH4GG6GGKKV3TDHRL5R4TRAK2","short_pith_number":"pith:JZH4GG6G","schema_version":"1.0","canonical_sha256":"4e4fc31bc632955dcc678afb1e4e205682a1487ce12994acfcd6e880d5c5d2b7","source":{"kind":"arxiv","id":"1907.09748","version":1},"attestation_state":"computed","paper":{"title":"Position Focused Attention Network for Image-Text Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Biao Li, Hao Yang, Jing Lu, Lin Ma, Xin Fan, Xueming Qian, Yaxiong Wang","submitted_at":"2019-07-23T08:23:42Z","abstract_excerpt":"Image-text matching tasks have recently attracted a lot of attention in the computer vision field. The key point of this cross-domain problem is how to accurately measure the similarity between the visual and the textual contents, which demands a fine understanding of both modalities. In this paper, we propose a novel position focused attention network (PFAN) to investigate the relation between the visual and the textual views. In this work, we integrate the object position clue to enhance the visual-text joint-embedding learning. We first split the images into blocks, by which we infer the re"},"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":"1907.09748","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-23T08:23:42Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"bd28e8f7a3f1b4549e061a262d2b1b46daf7c5359d8b877b708f549765e160d9","abstract_canon_sha256":"8dec193d3cde62194d05e4f0dcf5cd66a5e72ffe58bef141a3bbabe1a5e87fc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:50.177333Z","signature_b64":"fA6nXcl5Q+wqcJNWvvFzWgU9i5gl8qGNGFJ03lhP0+UBgZQjstrUoKLc5JWtiho0ODC81PdAWTyoK5xGLEGGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e4fc31bc632955dcc678afb1e4e205682a1487ce12994acfcd6e880d5c5d2b7","last_reissued_at":"2026-05-17T23:39:50.176639Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:50.176639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position Focused Attention Network for Image-Text Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Biao Li, Hao Yang, Jing Lu, Lin Ma, Xin Fan, Xueming Qian, Yaxiong Wang","submitted_at":"2019-07-23T08:23:42Z","abstract_excerpt":"Image-text matching tasks have recently attracted a lot of attention in the computer vision field. The key point of this cross-domain problem is how to accurately measure the similarity between the visual and the textual contents, which demands a fine understanding of both modalities. In this paper, we propose a novel position focused attention network (PFAN) to investigate the relation between the visual and the textual views. In this work, we integrate the object position clue to enhance the visual-text joint-embedding learning. We first split the images into blocks, by which we infer the re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.09748","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":"1907.09748","created_at":"2026-05-17T23:39:50.176745+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.09748v1","created_at":"2026-05-17T23:39:50.176745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.09748","created_at":"2026-05-17T23:39:50.176745+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZH4GG6GGKKV","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZH4GG6GGKKV3TDH","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZH4GG6G","created_at":"2026-05-18T12:33:21.387695+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/JZH4GG6GGKKV3TDHRL5R4TRAK2","json":"https://pith.science/pith/JZH4GG6GGKKV3TDHRL5R4TRAK2.json","graph_json":"https://pith.science/api/pith-number/JZH4GG6GGKKV3TDHRL5R4TRAK2/graph.json","events_json":"https://pith.science/api/pith-number/JZH4GG6GGKKV3TDHRL5R4TRAK2/events.json","paper":"https://pith.science/paper/JZH4GG6G"},"agent_actions":{"view_html":"https://pith.science/pith/JZH4GG6GGKKV3TDHRL5R4TRAK2","download_json":"https://pith.science/pith/JZH4GG6GGKKV3TDHRL5R4TRAK2.json","view_paper":"https://pith.science/paper/JZH4GG6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.09748&json=true","fetch_graph":"https://pith.science/api/pith-number/JZH4GG6GGKKV3TDHRL5R4TRAK2/graph.json","fetch_events":"https://pith.science/api/pith-number/JZH4GG6GGKKV3TDHRL5R4TRAK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZH4GG6GGKKV3TDHRL5R4TRAK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZH4GG6GGKKV3TDHRL5R4TRAK2/action/storage_attestation","attest_author":"https://pith.science/pith/JZH4GG6GGKKV3TDHRL5R4TRAK2/action/author_attestation","sign_citation":"https://pith.science/pith/JZH4GG6GGKKV3TDHRL5R4TRAK2/action/citation_signature","submit_replication":"https://pith.science/pith/JZH4GG6GGKKV3TDHRL5R4TRAK2/action/replication_record"}},"created_at":"2026-05-17T23:39:50.176745+00:00","updated_at":"2026-05-17T23:39:50.176745+00:00"}