{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3SJZ45X2UCLY445FEYNGWLMNQM","short_pith_number":"pith:3SJZ45X2","schema_version":"1.0","canonical_sha256":"dc939e76faa0978e73a5261a6b2d8d831a695f7913d3d88940617a64af80dc2a","source":{"kind":"arxiv","id":"1905.07841","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Transformer with Multi-View Visual Representation for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Li, Jun Yu, Qingming Huang, Zhou Yu","submitted_at":"2019-05-20T01:56:06Z","abstract_excerpt":"Image captioning aims to automatically generate a natural language description of a given image, and most state-of-the-art models have adopted an encoder-decoder framework. The framework consists of a convolution neural network (CNN)-based image encoder that extracts region-based visual features from the input image, and an recurrent neural network (RNN)-based caption decoder that generates the output caption words based on the visual features with the attention mechanism. Despite the success of existing studies, current methods only model the co-attention that characterizes the inter-modal in"},"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":"1905.07841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T01:56:06Z","cross_cats_sorted":[],"title_canon_sha256":"ea22c16804b133e556e3bc0691fc24377772874bca707e891d0bc70fe935d410","abstract_canon_sha256":"ea75bb97eedceed96f80c00d72908290e704a03e1506a3ae88db33f90f5fc32e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:48.368616Z","signature_b64":"l8kePOkpRPFppyS/X9fz3VFdDtUmnJ21BHxPH322dONAXCI7b7ajTKnkG0G9dYFaPpp1L5MVBiRMuNi7HIrPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc939e76faa0978e73a5261a6b2d8d831a695f7913d3d88940617a64af80dc2a","last_reissued_at":"2026-05-17T23:45:48.368104Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:48.368104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Transformer with Multi-View Visual Representation for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Li, Jun Yu, Qingming Huang, Zhou Yu","submitted_at":"2019-05-20T01:56:06Z","abstract_excerpt":"Image captioning aims to automatically generate a natural language description of a given image, and most state-of-the-art models have adopted an encoder-decoder framework. The framework consists of a convolution neural network (CNN)-based image encoder that extracts region-based visual features from the input image, and an recurrent neural network (RNN)-based caption decoder that generates the output caption words based on the visual features with the attention mechanism. Despite the success of existing studies, current methods only model the co-attention that characterizes the inter-modal in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07841","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":"1905.07841","created_at":"2026-05-17T23:45:48.368203+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.07841v1","created_at":"2026-05-17T23:45:48.368203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07841","created_at":"2026-05-17T23:45:48.368203+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SJZ45X2UCLY","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SJZ45X2UCLY445F","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SJZ45X2","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.03557","citing_title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM","json":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM.json","graph_json":"https://pith.science/api/pith-number/3SJZ45X2UCLY445FEYNGWLMNQM/graph.json","events_json":"https://pith.science/api/pith-number/3SJZ45X2UCLY445FEYNGWLMNQM/events.json","paper":"https://pith.science/paper/3SJZ45X2"},"agent_actions":{"view_html":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM","download_json":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM.json","view_paper":"https://pith.science/paper/3SJZ45X2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.07841&json=true","fetch_graph":"https://pith.science/api/pith-number/3SJZ45X2UCLY445FEYNGWLMNQM/graph.json","fetch_events":"https://pith.science/api/pith-number/3SJZ45X2UCLY445FEYNGWLMNQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM/action/storage_attestation","attest_author":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM/action/author_attestation","sign_citation":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM/action/citation_signature","submit_replication":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM/action/replication_record"}},"created_at":"2026-05-17T23:45:48.368203+00:00","updated_at":"2026-05-17T23:45:48.368203+00:00"}