{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GMY4GG6W7BZI2PSUJBCQHV6PYH","short_pith_number":"pith:GMY4GG6W","schema_version":"1.0","canonical_sha256":"3331c31bd6f8728d3e54484503d7cfc1d2b8ab2b468674cae54ce01b2a7bb3d8","source":{"kind":"arxiv","id":"1802.02892","version":1},"attestation_state":"computed","paper":{"title":"Efficient Large-Scale Multi-Modal Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"A. Joulin, D. Kiela, E. Grave, T. Mikolov","submitted_at":"2018-02-06T20:30:59Z","abstract_excerpt":"While the incipient internet was largely text-based, the modern digital world is becoming increasingly multi-modal. Here, we examine multi-modal classification where one modality is discrete, e.g. text, and the other is continuous, e.g. visual representations transferred from a convolutional neural network. In particular, we focus on scenarios where we have to be able to classify large quantities of data quickly. We investigate various methods for performing multi-modal fusion and analyze their trade-offs in terms of classification accuracy and computational efficiency. Our findings indicate t"},"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":"1802.02892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-06T20:30:59Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"bedaf9d604440a1bafcfa4a44b18a4aa754e45feb560ffbb4f3238a4c1ef8558","abstract_canon_sha256":"38e91def78e626b9cb9bd165631e1a485b186a97f0db7b173debc48c597f0522"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:02.865840Z","signature_b64":"P2RMLRiCRlEBVlvm+zHzbml8M2nObVKdXNBEDenImv4BDcVmaYVC9GvOgFbXPTWi+sEDwJeHODMN/eNQaAeuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3331c31bd6f8728d3e54484503d7cfc1d2b8ab2b468674cae54ce01b2a7bb3d8","last_reissued_at":"2026-05-18T00:24:02.865393Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:02.865393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Large-Scale Multi-Modal Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"A. Joulin, D. Kiela, E. Grave, T. Mikolov","submitted_at":"2018-02-06T20:30:59Z","abstract_excerpt":"While the incipient internet was largely text-based, the modern digital world is becoming increasingly multi-modal. Here, we examine multi-modal classification where one modality is discrete, e.g. text, and the other is continuous, e.g. visual representations transferred from a convolutional neural network. In particular, we focus on scenarios where we have to be able to classify large quantities of data quickly. We investigate various methods for performing multi-modal fusion and analyze their trade-offs in terms of classification accuracy and computational efficiency. Our findings indicate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02892","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":"1802.02892","created_at":"2026-05-18T00:24:02.865463+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.02892v1","created_at":"2026-05-18T00:24:02.865463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02892","created_at":"2026-05-18T00:24:02.865463+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMY4GG6W7BZI","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMY4GG6W7BZI2PSU","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMY4GG6W","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":"1906.12120","citing_title":"One Embedding To Do Them All","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMY4GG6W7BZI2PSUJBCQHV6PYH","json":"https://pith.science/pith/GMY4GG6W7BZI2PSUJBCQHV6PYH.json","graph_json":"https://pith.science/api/pith-number/GMY4GG6W7BZI2PSUJBCQHV6PYH/graph.json","events_json":"https://pith.science/api/pith-number/GMY4GG6W7BZI2PSUJBCQHV6PYH/events.json","paper":"https://pith.science/paper/GMY4GG6W"},"agent_actions":{"view_html":"https://pith.science/pith/GMY4GG6W7BZI2PSUJBCQHV6PYH","download_json":"https://pith.science/pith/GMY4GG6W7BZI2PSUJBCQHV6PYH.json","view_paper":"https://pith.science/paper/GMY4GG6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.02892&json=true","fetch_graph":"https://pith.science/api/pith-number/GMY4GG6W7BZI2PSUJBCQHV6PYH/graph.json","fetch_events":"https://pith.science/api/pith-number/GMY4GG6W7BZI2PSUJBCQHV6PYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMY4GG6W7BZI2PSUJBCQHV6PYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMY4GG6W7BZI2PSUJBCQHV6PYH/action/storage_attestation","attest_author":"https://pith.science/pith/GMY4GG6W7BZI2PSUJBCQHV6PYH/action/author_attestation","sign_citation":"https://pith.science/pith/GMY4GG6W7BZI2PSUJBCQHV6PYH/action/citation_signature","submit_replication":"https://pith.science/pith/GMY4GG6W7BZI2PSUJBCQHV6PYH/action/replication_record"}},"created_at":"2026-05-18T00:24:02.865463+00:00","updated_at":"2026-05-18T00:24:02.865463+00:00"}