{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JJ6V6YGANYILERQT4CUPOPR7UL","short_pith_number":"pith:JJ6V6YGA","schema_version":"1.0","canonical_sha256":"4a7d5f60c06e10b24613e0a8f73e3fa2ee8537d7df79621222b39da661d834e0","source":{"kind":"arxiv","id":"1604.00790","version":3},"attestation_state":"computed","paper":{"title":"Image Captioning with Deep Bidirectional LSTMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Cheng Wang, Christian Bartz, Christoph Meinel, Haojin Yang","submitted_at":"2016-04-04T09:43:04Z","abstract_excerpt":"This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning. Our model builds on a deep convolutional neural network (CNN) and two separate LSTM networks. It is capable of learning long term visual-language interactions by making use of history and future context information at high level semantic space. Two novel deep bidirectional variant models, in which we increase the depth of nonlinearity transition in different way, are proposed to learn hierarchical visual-language embeddings. Data augmentation techniques such as multi-crop, mu"},"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":"1604.00790","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-04T09:43:04Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"3c95cc3c2469f3904eab06e64dc543135f382cf731788a57a8c5c79af21d973c","abstract_canon_sha256":"c9219cdebf7b2f19d75e2c73cab1936b2f3edbbf00ad6af40b5ee4ab5bcc9aaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:45.621088Z","signature_b64":"uy/OQmhkbmku/zYSGp5XymNOVxgWjRKYaKuPR07QGiZQMhok6XiJOuHPWztHJEWLZ8D574hAcQahiWbiA5D1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a7d5f60c06e10b24613e0a8f73e3fa2ee8537d7df79621222b39da661d834e0","last_reissued_at":"2026-05-18T01:10:45.620659Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:45.620659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Captioning with Deep Bidirectional LSTMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Cheng Wang, Christian Bartz, Christoph Meinel, Haojin Yang","submitted_at":"2016-04-04T09:43:04Z","abstract_excerpt":"This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning. Our model builds on a deep convolutional neural network (CNN) and two separate LSTM networks. It is capable of learning long term visual-language interactions by making use of history and future context information at high level semantic space. Two novel deep bidirectional variant models, in which we increase the depth of nonlinearity transition in different way, are proposed to learn hierarchical visual-language embeddings. Data augmentation techniques such as multi-crop, mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00790","kind":"arxiv","version":3},"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":"1604.00790","created_at":"2026-05-18T01:10:45.620720+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.00790v3","created_at":"2026-05-18T01:10:45.620720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00790","created_at":"2026-05-18T01:10:45.620720+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJ6V6YGANYIL","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJ6V6YGANYILERQT","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJ6V6YGA","created_at":"2026-05-18T12:30:25.849896+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/JJ6V6YGANYILERQT4CUPOPR7UL","json":"https://pith.science/pith/JJ6V6YGANYILERQT4CUPOPR7UL.json","graph_json":"https://pith.science/api/pith-number/JJ6V6YGANYILERQT4CUPOPR7UL/graph.json","events_json":"https://pith.science/api/pith-number/JJ6V6YGANYILERQT4CUPOPR7UL/events.json","paper":"https://pith.science/paper/JJ6V6YGA"},"agent_actions":{"view_html":"https://pith.science/pith/JJ6V6YGANYILERQT4CUPOPR7UL","download_json":"https://pith.science/pith/JJ6V6YGANYILERQT4CUPOPR7UL.json","view_paper":"https://pith.science/paper/JJ6V6YGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.00790&json=true","fetch_graph":"https://pith.science/api/pith-number/JJ6V6YGANYILERQT4CUPOPR7UL/graph.json","fetch_events":"https://pith.science/api/pith-number/JJ6V6YGANYILERQT4CUPOPR7UL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJ6V6YGANYILERQT4CUPOPR7UL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJ6V6YGANYILERQT4CUPOPR7UL/action/storage_attestation","attest_author":"https://pith.science/pith/JJ6V6YGANYILERQT4CUPOPR7UL/action/author_attestation","sign_citation":"https://pith.science/pith/JJ6V6YGANYILERQT4CUPOPR7UL/action/citation_signature","submit_replication":"https://pith.science/pith/JJ6V6YGANYILERQT4CUPOPR7UL/action/replication_record"}},"created_at":"2026-05-18T01:10:45.620720+00:00","updated_at":"2026-05-18T01:10:45.620720+00:00"}