{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PHE45N55NK7FR5T7XECBIEOE63","short_pith_number":"pith:PHE45N55","schema_version":"1.0","canonical_sha256":"79c9ceb7bd6abe58f67fb9041411c4f6fd881dbe5403a1a3b49d6fb669b64ae9","source":{"kind":"arxiv","id":"1904.00767","version":1},"attestation_state":"computed","paper":{"title":"Boosted Attention: Leveraging Human Attention for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qi Zhao, Shi Chen","submitted_at":"2019-03-18T15:59:44Z","abstract_excerpt":"Visual attention has shown usefulness in image captioning, with the goal of enabling a caption model to selectively focus on regions of interest. Existing models typically rely on top-down language information and learn attention implicitly by optimizing the captioning objectives. While somewhat effective, the learned top-down attention can fail to focus on correct regions of interest without direct supervision of attention. Inspired by the human visual system which is driven by not only the task-specific top-down signals but also the visual stimuli, we in this work propose to use both types o"},"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":"1904.00767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T15:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"fae8d6b50c09b22ea52fdd1e595b5325b31bc08ecbb57da7b055e49660005f0c","abstract_canon_sha256":"86f6eab4ae3c03524f43d52e95fea3a0b8ce6fd094943e8f39f4524c11073fe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:45.513491Z","signature_b64":"r3P9qVgdk+lDae9j/uXnxPxlJ5dr08gKWPEXJRrNdNaHBAh+0pcoJ0UHshJEFuprR5ERsbFIZEuE7exEbVGyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79c9ceb7bd6abe58f67fb9041411c4f6fd881dbe5403a1a3b49d6fb669b64ae9","last_reissued_at":"2026-05-17T23:49:45.512598Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:45.512598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosted Attention: Leveraging Human Attention for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qi Zhao, Shi Chen","submitted_at":"2019-03-18T15:59:44Z","abstract_excerpt":"Visual attention has shown usefulness in image captioning, with the goal of enabling a caption model to selectively focus on regions of interest. Existing models typically rely on top-down language information and learn attention implicitly by optimizing the captioning objectives. While somewhat effective, the learned top-down attention can fail to focus on correct regions of interest without direct supervision of attention. Inspired by the human visual system which is driven by not only the task-specific top-down signals but also the visual stimuli, we in this work propose to use both types o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.00767","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":"1904.00767","created_at":"2026-05-17T23:49:45.512750+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.00767v1","created_at":"2026-05-17T23:49:45.512750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.00767","created_at":"2026-05-17T23:49:45.512750+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHE45N55NK7F","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHE45N55NK7FR5T7","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHE45N55","created_at":"2026-05-18T12:33:24.271573+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/PHE45N55NK7FR5T7XECBIEOE63","json":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63.json","graph_json":"https://pith.science/api/pith-number/PHE45N55NK7FR5T7XECBIEOE63/graph.json","events_json":"https://pith.science/api/pith-number/PHE45N55NK7FR5T7XECBIEOE63/events.json","paper":"https://pith.science/paper/PHE45N55"},"agent_actions":{"view_html":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63","download_json":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63.json","view_paper":"https://pith.science/paper/PHE45N55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.00767&json=true","fetch_graph":"https://pith.science/api/pith-number/PHE45N55NK7FR5T7XECBIEOE63/graph.json","fetch_events":"https://pith.science/api/pith-number/PHE45N55NK7FR5T7XECBIEOE63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63/action/storage_attestation","attest_author":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63/action/author_attestation","sign_citation":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63/action/citation_signature","submit_replication":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63/action/replication_record"}},"created_at":"2026-05-17T23:49:45.512750+00:00","updated_at":"2026-05-17T23:49:45.512750+00:00"}