{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GPAL7UTGOLHKDAVCCLAWFQGOZN","short_pith_number":"pith:GPAL7UTG","schema_version":"1.0","canonical_sha256":"33c0bfd26672cea182a212c162c0cecb6cf141e9b7e966544443dc9660eaadcd","source":{"kind":"arxiv","id":"1803.08024","version":2},"attestation_state":"computed","paper":{"title":"Stacked Cross Attention for Image-Text Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gang Hua, Houdong Hu, Kuang-Huei Lee, Xiaodong He, Xi Chen","submitted_at":"2018-03-21T17:22:27Z","abstract_excerpt":"In this paper, we study the problem of image-text matching. Inferring the latent semantic alignment between objects or other salient stuff (e.g. snow, sky, lawn) and the corresponding words in sentences allows to capture fine-grained interplay between vision and language, and makes image-text matching more interpretable. Prior work either simply aggregates the similarity of all possible pairs of regions and words without attending differentially to more and less important words or regions, or uses a multi-step attentional process to capture limited number of semantic alignments which is less i"},"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":"1803.08024","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-21T17:22:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"680b85818339fd659a74e35242315f864bf9e5e81dfaaa5f65d1330d282e5b6c","abstract_canon_sha256":"f1b54996692c348f37c91bfc7a22e257c7b9de5687cc55a427723d0518b678df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:10.468844Z","signature_b64":"cg2huYD12PJRf4VAaX9fUVlgtnUoTGLebADi3LQHWiQkkSFv8Pzk6v/xt0cWowmZjN0N0NUfPEopQz5dkuG/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33c0bfd26672cea182a212c162c0cecb6cf141e9b7e966544443dc9660eaadcd","last_reissued_at":"2026-05-18T00:10:10.468111Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:10.468111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stacked Cross Attention for Image-Text Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gang Hua, Houdong Hu, Kuang-Huei Lee, Xiaodong He, Xi Chen","submitted_at":"2018-03-21T17:22:27Z","abstract_excerpt":"In this paper, we study the problem of image-text matching. Inferring the latent semantic alignment between objects or other salient stuff (e.g. snow, sky, lawn) and the corresponding words in sentences allows to capture fine-grained interplay between vision and language, and makes image-text matching more interpretable. Prior work either simply aggregates the similarity of all possible pairs of regions and words without attending differentially to more and less important words or regions, or uses a multi-step attentional process to capture limited number of semantic alignments which is less i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08024","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":""},"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":"1803.08024","created_at":"2026-05-18T00:10:10.468223+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.08024v2","created_at":"2026-05-18T00:10:10.468223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08024","created_at":"2026-05-18T00:10:10.468223+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPAL7UTGOLHK","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPAL7UTGOLHKDAVC","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPAL7UTG","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.02072","citing_title":"Large-scale Tag-based Font Retrieval with Generative Feature Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPAL7UTGOLHKDAVCCLAWFQGOZN","json":"https://pith.science/pith/GPAL7UTGOLHKDAVCCLAWFQGOZN.json","graph_json":"https://pith.science/api/pith-number/GPAL7UTGOLHKDAVCCLAWFQGOZN/graph.json","events_json":"https://pith.science/api/pith-number/GPAL7UTGOLHKDAVCCLAWFQGOZN/events.json","paper":"https://pith.science/paper/GPAL7UTG"},"agent_actions":{"view_html":"https://pith.science/pith/GPAL7UTGOLHKDAVCCLAWFQGOZN","download_json":"https://pith.science/pith/GPAL7UTGOLHKDAVCCLAWFQGOZN.json","view_paper":"https://pith.science/paper/GPAL7UTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.08024&json=true","fetch_graph":"https://pith.science/api/pith-number/GPAL7UTGOLHKDAVCCLAWFQGOZN/graph.json","fetch_events":"https://pith.science/api/pith-number/GPAL7UTGOLHKDAVCCLAWFQGOZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPAL7UTGOLHKDAVCCLAWFQGOZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPAL7UTGOLHKDAVCCLAWFQGOZN/action/storage_attestation","attest_author":"https://pith.science/pith/GPAL7UTGOLHKDAVCCLAWFQGOZN/action/author_attestation","sign_citation":"https://pith.science/pith/GPAL7UTGOLHKDAVCCLAWFQGOZN/action/citation_signature","submit_replication":"https://pith.science/pith/GPAL7UTGOLHKDAVCCLAWFQGOZN/action/replication_record"}},"created_at":"2026-05-18T00:10:10.468223+00:00","updated_at":"2026-05-18T00:10:10.468223+00:00"}