{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LIADIDIJO77BEIW7THEX6KMAH7","short_pith_number":"pith:LIADIDIJ","schema_version":"1.0","canonical_sha256":"5a00340d0977fe1222df99c97f29803fed1ff7e8e7a9c829a32d76a63efb2c22","source":{"kind":"arxiv","id":"1701.06521","version":1},"attestation_state":"computed","paper":{"title":"Incorporating Global Visual Features into Attention-Based Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iacer Calixto, Nick Campbell, Qun Liu","submitted_at":"2017-01-23T17:43:23Z","abstract_excerpt":"We introduce multi-modal, attention-based neural machine translation (NMT) models which incorporate visual features into different parts of both the encoder and the decoder. We utilise global image features extracted using a pre-trained convolutional neural network and incorporate them (i) as words in the source sentence, (ii) to initialise the encoder hidden state, and (iii) as additional data to initialise the decoder hidden state. In our experiments, we evaluate how these different strategies to incorporate global image features compare and which ones perform best. We also study the impact "},"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":"1701.06521","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-23T17:43:23Z","cross_cats_sorted":[],"title_canon_sha256":"95fd940085adc13ac72a05d598b16615ccc730ace0ee7ebc01052887dd7e8fa2","abstract_canon_sha256":"a23397fc107e87fdee9caa7eaab008c933daa0d0238a4a4f23b12c8f7b999739"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:18.168277Z","signature_b64":"7g5Mxzwk2oXOugseYerS46PdWmmy0dHd5d9cZDi4jYQn9SfuDUUUj3UE4+hwIWPXC1PXwDlOYWa1tN/Z43wpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a00340d0977fe1222df99c97f29803fed1ff7e8e7a9c829a32d76a63efb2c22","last_reissued_at":"2026-05-18T00:52:18.167646Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:18.167646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Global Visual Features into Attention-Based Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iacer Calixto, Nick Campbell, Qun Liu","submitted_at":"2017-01-23T17:43:23Z","abstract_excerpt":"We introduce multi-modal, attention-based neural machine translation (NMT) models which incorporate visual features into different parts of both the encoder and the decoder. We utilise global image features extracted using a pre-trained convolutional neural network and incorporate them (i) as words in the source sentence, (ii) to initialise the encoder hidden state, and (iii) as additional data to initialise the decoder hidden state. In our experiments, we evaluate how these different strategies to incorporate global image features compare and which ones perform best. We also study the impact "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.06521","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":"1701.06521","created_at":"2026-05-18T00:52:18.167724+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.06521v1","created_at":"2026-05-18T00:52:18.167724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.06521","created_at":"2026-05-18T00:52:18.167724+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIADIDIJO77B","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIADIDIJO77BEIW7","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIADIDIJ","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06789","citing_title":"Video-guided Machine Translation with Global Video Context","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIADIDIJO77BEIW7THEX6KMAH7","json":"https://pith.science/pith/LIADIDIJO77BEIW7THEX6KMAH7.json","graph_json":"https://pith.science/api/pith-number/LIADIDIJO77BEIW7THEX6KMAH7/graph.json","events_json":"https://pith.science/api/pith-number/LIADIDIJO77BEIW7THEX6KMAH7/events.json","paper":"https://pith.science/paper/LIADIDIJ"},"agent_actions":{"view_html":"https://pith.science/pith/LIADIDIJO77BEIW7THEX6KMAH7","download_json":"https://pith.science/pith/LIADIDIJO77BEIW7THEX6KMAH7.json","view_paper":"https://pith.science/paper/LIADIDIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.06521&json=true","fetch_graph":"https://pith.science/api/pith-number/LIADIDIJO77BEIW7THEX6KMAH7/graph.json","fetch_events":"https://pith.science/api/pith-number/LIADIDIJO77BEIW7THEX6KMAH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIADIDIJO77BEIW7THEX6KMAH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIADIDIJO77BEIW7THEX6KMAH7/action/storage_attestation","attest_author":"https://pith.science/pith/LIADIDIJO77BEIW7THEX6KMAH7/action/author_attestation","sign_citation":"https://pith.science/pith/LIADIDIJO77BEIW7THEX6KMAH7/action/citation_signature","submit_replication":"https://pith.science/pith/LIADIDIJO77BEIW7THEX6KMAH7/action/replication_record"}},"created_at":"2026-05-18T00:52:18.167724+00:00","updated_at":"2026-05-18T00:52:18.167724+00:00"}