{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:G5WZ4U3KO3UX7VS4K2SH4LXXMH","short_pith_number":"pith:G5WZ4U3K","schema_version":"1.0","canonical_sha256":"376d9e536a76e97fd65c56a47e2ef761fd0e13eff949b14a68653c653ca2f321","source":{"kind":"arxiv","id":"1603.02814","version":2},"attestation_state":"computed","paper":{"title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anthony Dick, Anton van den Hengel, Chunhua Shen, Peng Wang, Qi Wu","submitted_at":"2016-03-09T08:56:45Z","abstract_excerpt":"Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism ca"},"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":"1603.02814","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-09T08:56:45Z","cross_cats_sorted":[],"title_canon_sha256":"8c7d3bbb3c84b4ee49cfa1e8124b6f6ace0dd2bd64b15d70467439e55ec2e80a","abstract_canon_sha256":"34aeec0f994bb5719cde0db7099dbba8808689bb03862265fab837b1eff564ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:52.861259Z","signature_b64":"SOCBCh73ZHwuXY7XCqp3QTpFMK+KiKTo3RCvrzH96suwGmLUcgLiTYY6rf1ZdkALgPGLauLfcJJhL9j4jRpGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"376d9e536a76e97fd65c56a47e2ef761fd0e13eff949b14a68653c653ca2f321","last_reissued_at":"2026-05-18T00:54:52.860861Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:52.860861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anthony Dick, Anton van den Hengel, Chunhua Shen, Peng Wang, Qi Wu","submitted_at":"2016-03-09T08:56:45Z","abstract_excerpt":"Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.02814","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":"1603.02814","created_at":"2026-05-18T00:54:52.860921+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.02814v2","created_at":"2026-05-18T00:54:52.860921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.02814","created_at":"2026-05-18T00:54:52.860921+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5WZ4U3KO3UX","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5WZ4U3KO3UX7VS4","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5WZ4U3K","created_at":"2026-05-18T12:30:15.759754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22933","citing_title":"Augmented Vision-Language Models: A Systematic Review","ref_index":117,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH","json":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH.json","graph_json":"https://pith.science/api/pith-number/G5WZ4U3KO3UX7VS4K2SH4LXXMH/graph.json","events_json":"https://pith.science/api/pith-number/G5WZ4U3KO3UX7VS4K2SH4LXXMH/events.json","paper":"https://pith.science/paper/G5WZ4U3K"},"agent_actions":{"view_html":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH","download_json":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH.json","view_paper":"https://pith.science/paper/G5WZ4U3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.02814&json=true","fetch_graph":"https://pith.science/api/pith-number/G5WZ4U3KO3UX7VS4K2SH4LXXMH/graph.json","fetch_events":"https://pith.science/api/pith-number/G5WZ4U3KO3UX7VS4K2SH4LXXMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/action/storage_attestation","attest_author":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/action/author_attestation","sign_citation":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/action/citation_signature","submit_replication":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/action/replication_record"}},"created_at":"2026-05-18T00:54:52.860921+00:00","updated_at":"2026-05-18T00:54:52.860921+00:00"}