{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NEXVODPJZIHAGPRN5ZU5WIOV6W","short_pith_number":"pith:NEXVODPJ","schema_version":"1.0","canonical_sha256":"692f570de9ca0e033e2dee69db21d5f58c7de6527e9916b2fa8c0bb2ca4e3b3b","source":{"kind":"arxiv","id":"1709.06308","version":1},"attestation_state":"computed","paper":{"title":"Exploring Human-like Attention Supervision in Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duanqing Xu, Jianfeng Dong, Tingting Qiao","submitted_at":"2017-09-19T09:19:08Z","abstract_excerpt":"Attention mechanisms have been widely applied in the Visual Question Answering (VQA) task, as they help to focus on the area-of-interest of both visual and textual information. To answer the questions correctly, the model needs to selectively target different areas of an image, which suggests that an attention-based model may benefit from an explicit attention supervision. In this work, we aim to address the problem of adding attention supervision to VQA models. Since there is a lack of human attention data, we first propose a Human Attention Network (HAN) to generate human-like attention maps"},"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":"1709.06308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-19T09:19:08Z","cross_cats_sorted":[],"title_canon_sha256":"6426e931371b193dd580817635075121899d74c4fee0acfc712365be6f638d0b","abstract_canon_sha256":"6e80468ade4444e6fe771ab0a376e3ac811ed48d5a51aae9eaffacfff0d788e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:53.605142Z","signature_b64":"wTkL5Ns+5bnj/MhorXrAEm7kg6n6uoRuC6bvvrEL+090kpAgklwefH58bMUFiC6aCrrWlaaYdKFPlS9lZL57AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"692f570de9ca0e033e2dee69db21d5f58c7de6527e9916b2fa8c0bb2ca4e3b3b","last_reissued_at":"2026-05-18T00:34:53.604445Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:53.604445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Human-like Attention Supervision in Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duanqing Xu, Jianfeng Dong, Tingting Qiao","submitted_at":"2017-09-19T09:19:08Z","abstract_excerpt":"Attention mechanisms have been widely applied in the Visual Question Answering (VQA) task, as they help to focus on the area-of-interest of both visual and textual information. To answer the questions correctly, the model needs to selectively target different areas of an image, which suggests that an attention-based model may benefit from an explicit attention supervision. In this work, we aim to address the problem of adding attention supervision to VQA models. Since there is a lack of human attention data, we first propose a Human Attention Network (HAN) to generate human-like attention maps"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06308","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":"1709.06308","created_at":"2026-05-18T00:34:53.604552+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.06308v1","created_at":"2026-05-18T00:34:53.604552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06308","created_at":"2026-05-18T00:34:53.604552+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEXVODPJZIHA","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEXVODPJZIHAGPRN","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEXVODPJ","created_at":"2026-05-18T12:31:31.346846+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/NEXVODPJZIHAGPRN5ZU5WIOV6W","json":"https://pith.science/pith/NEXVODPJZIHAGPRN5ZU5WIOV6W.json","graph_json":"https://pith.science/api/pith-number/NEXVODPJZIHAGPRN5ZU5WIOV6W/graph.json","events_json":"https://pith.science/api/pith-number/NEXVODPJZIHAGPRN5ZU5WIOV6W/events.json","paper":"https://pith.science/paper/NEXVODPJ"},"agent_actions":{"view_html":"https://pith.science/pith/NEXVODPJZIHAGPRN5ZU5WIOV6W","download_json":"https://pith.science/pith/NEXVODPJZIHAGPRN5ZU5WIOV6W.json","view_paper":"https://pith.science/paper/NEXVODPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.06308&json=true","fetch_graph":"https://pith.science/api/pith-number/NEXVODPJZIHAGPRN5ZU5WIOV6W/graph.json","fetch_events":"https://pith.science/api/pith-number/NEXVODPJZIHAGPRN5ZU5WIOV6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEXVODPJZIHAGPRN5ZU5WIOV6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEXVODPJZIHAGPRN5ZU5WIOV6W/action/storage_attestation","attest_author":"https://pith.science/pith/NEXVODPJZIHAGPRN5ZU5WIOV6W/action/author_attestation","sign_citation":"https://pith.science/pith/NEXVODPJZIHAGPRN5ZU5WIOV6W/action/citation_signature","submit_replication":"https://pith.science/pith/NEXVODPJZIHAGPRN5ZU5WIOV6W/action/replication_record"}},"created_at":"2026-05-18T00:34:53.604552+00:00","updated_at":"2026-05-18T00:34:53.604552+00:00"}