{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UAWXLVH55HQ6G42E3B6KY3TGBW","short_pith_number":"pith:UAWXLVH5","schema_version":"1.0","canonical_sha256":"a02d75d4fde9e1e37344d87cac6e660da6bc2f83a7af805d37bc45248791fe20","source":{"kind":"arxiv","id":"1804.01720","version":2},"attestation_state":"computed","paper":{"title":"Finding beans in burgers: Deep semantic-visual embedding with localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Louis Chevallier, Martin Engilberge, Matthieu Cord, Patrick P\\'erez","submitted_at":"2018-04-05T08:13:37Z","abstract_excerpt":"Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry captures useful semantic relationships. Such a multi-modal embedding can be trained and used for various tasks, notably image captioning. In the present work, we introduce a new architecture of this type, with a visual path that leverages recent space-aware pooling mechanisms. Combined with a textual path which is jointly trained from scratch, our semantic-visual embedding offers a versatile model. Once trained under the supervision of caption"},"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":"1804.01720","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-05T08:13:37Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"73ae855a45f0e7f48f1631a5c77b7ebe8e9133f1ca0894bdd3f8cbfe286a1e65","abstract_canon_sha256":"1ed70ce9004c2a367b1b0be3be45b48866e76f1a9dc6e18099f7ad0aa7fec79f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:08.135177Z","signature_b64":"hfN8ayKRjqjI8AilLGjLXkbPrNeNNsoO6RQTaocoSY0jbIMQHnyuRbrJu08N2/elPyoahiipSqekwWSPOcANBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a02d75d4fde9e1e37344d87cac6e660da6bc2f83a7af805d37bc45248791fe20","last_reissued_at":"2026-05-18T00:19:08.134468Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:08.134468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding beans in burgers: Deep semantic-visual embedding with localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Louis Chevallier, Martin Engilberge, Matthieu Cord, Patrick P\\'erez","submitted_at":"2018-04-05T08:13:37Z","abstract_excerpt":"Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry captures useful semantic relationships. Such a multi-modal embedding can be trained and used for various tasks, notably image captioning. In the present work, we introduce a new architecture of this type, with a visual path that leverages recent space-aware pooling mechanisms. Combined with a textual path which is jointly trained from scratch, our semantic-visual embedding offers a versatile model. Once trained under the supervision of caption"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01720","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":"1804.01720","created_at":"2026-05-18T00:19:08.134589+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.01720v2","created_at":"2026-05-18T00:19:08.134589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01720","created_at":"2026-05-18T00:19:08.134589+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAWXLVH55HQ6","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAWXLVH55HQ6G42E","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAWXLVH5","created_at":"2026-05-18T12:32:56.356000+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/UAWXLVH55HQ6G42E3B6KY3TGBW","json":"https://pith.science/pith/UAWXLVH55HQ6G42E3B6KY3TGBW.json","graph_json":"https://pith.science/api/pith-number/UAWXLVH55HQ6G42E3B6KY3TGBW/graph.json","events_json":"https://pith.science/api/pith-number/UAWXLVH55HQ6G42E3B6KY3TGBW/events.json","paper":"https://pith.science/paper/UAWXLVH5"},"agent_actions":{"view_html":"https://pith.science/pith/UAWXLVH55HQ6G42E3B6KY3TGBW","download_json":"https://pith.science/pith/UAWXLVH55HQ6G42E3B6KY3TGBW.json","view_paper":"https://pith.science/paper/UAWXLVH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.01720&json=true","fetch_graph":"https://pith.science/api/pith-number/UAWXLVH55HQ6G42E3B6KY3TGBW/graph.json","fetch_events":"https://pith.science/api/pith-number/UAWXLVH55HQ6G42E3B6KY3TGBW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAWXLVH55HQ6G42E3B6KY3TGBW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAWXLVH55HQ6G42E3B6KY3TGBW/action/storage_attestation","attest_author":"https://pith.science/pith/UAWXLVH55HQ6G42E3B6KY3TGBW/action/author_attestation","sign_citation":"https://pith.science/pith/UAWXLVH55HQ6G42E3B6KY3TGBW/action/citation_signature","submit_replication":"https://pith.science/pith/UAWXLVH55HQ6G42E3B6KY3TGBW/action/replication_record"}},"created_at":"2026-05-18T00:19:08.134589+00:00","updated_at":"2026-05-18T00:19:08.134589+00:00"}