{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:UD2VTUQKUJVGXLOGAAIHQ5QWIP","short_pith_number":"pith:UD2VTUQK","schema_version":"1.0","canonical_sha256":"a0f559d20aa26a6badc6001078761643e599105540054b25f684a9062e6ba802","source":{"kind":"arxiv","id":"1606.05589","version":1},"attestation_state":"computed","paper":{"title":"Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"stat.ML","authors_text":"Abhishek Das, C. Lawrence Zitnick, Devi Parikh, Dhruv Batra, Harsh Agrawal","submitted_at":"2016-06-17T17:00:02Z","abstract_excerpt":"We conduct large-scale studies on `human attention' in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation interfaces that require the subject to sharpen regions of a blurred image to answer a question. Thus, we introduce the VQA-HAT (Human ATtention) dataset. We evaluate attention maps generated by state-of-the-art VQA models against human attention both qualitatively (via visualizations) and quantitatively (via rank-order correlation). Overall, our experiments show tha"},"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":"1606.05589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T17:00:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d23bc869d0c98cda43d1be017143ea98bdef3a866179894440d14ff34243b503","abstract_canon_sha256":"ab16448293992d7b6e119da88c6964cb16c32c8a983c2696c53a6310f8c0c278"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:19.366448Z","signature_b64":"NojD7NbdvGL9lv0630p0TaJ/H/zPfGy24D7xfkphe2NbR0MSeKhU7qUsbT3KnlvzybH/nsjhwTK/3NR8MvK9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f559d20aa26a6badc6001078761643e599105540054b25f684a9062e6ba802","last_reissued_at":"2026-05-18T01:12:19.366088Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:19.366088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"stat.ML","authors_text":"Abhishek Das, C. Lawrence Zitnick, Devi Parikh, Dhruv Batra, Harsh Agrawal","submitted_at":"2016-06-17T17:00:02Z","abstract_excerpt":"We conduct large-scale studies on `human attention' in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation interfaces that require the subject to sharpen regions of a blurred image to answer a question. Thus, we introduce the VQA-HAT (Human ATtention) dataset. We evaluate attention maps generated by state-of-the-art VQA models against human attention both qualitatively (via visualizations) and quantitatively (via rank-order correlation). Overall, our experiments show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05589","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":"1606.05589","created_at":"2026-05-18T01:12:19.366147+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.05589v1","created_at":"2026-05-18T01:12:19.366147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05589","created_at":"2026-05-18T01:12:19.366147+00:00"},{"alias_kind":"pith_short_12","alias_value":"UD2VTUQKUJVG","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"UD2VTUQKUJVGXLOG","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"UD2VTUQK","created_at":"2026-05-18T12:30:46.583412+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/UD2VTUQKUJVGXLOGAAIHQ5QWIP","json":"https://pith.science/pith/UD2VTUQKUJVGXLOGAAIHQ5QWIP.json","graph_json":"https://pith.science/api/pith-number/UD2VTUQKUJVGXLOGAAIHQ5QWIP/graph.json","events_json":"https://pith.science/api/pith-number/UD2VTUQKUJVGXLOGAAIHQ5QWIP/events.json","paper":"https://pith.science/paper/UD2VTUQK"},"agent_actions":{"view_html":"https://pith.science/pith/UD2VTUQKUJVGXLOGAAIHQ5QWIP","download_json":"https://pith.science/pith/UD2VTUQKUJVGXLOGAAIHQ5QWIP.json","view_paper":"https://pith.science/paper/UD2VTUQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.05589&json=true","fetch_graph":"https://pith.science/api/pith-number/UD2VTUQKUJVGXLOGAAIHQ5QWIP/graph.json","fetch_events":"https://pith.science/api/pith-number/UD2VTUQKUJVGXLOGAAIHQ5QWIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UD2VTUQKUJVGXLOGAAIHQ5QWIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UD2VTUQKUJVGXLOGAAIHQ5QWIP/action/storage_attestation","attest_author":"https://pith.science/pith/UD2VTUQKUJVGXLOGAAIHQ5QWIP/action/author_attestation","sign_citation":"https://pith.science/pith/UD2VTUQKUJVGXLOGAAIHQ5QWIP/action/citation_signature","submit_replication":"https://pith.science/pith/UD2VTUQKUJVGXLOGAAIHQ5QWIP/action/replication_record"}},"created_at":"2026-05-18T01:12:19.366147+00:00","updated_at":"2026-05-18T01:12:19.366147+00:00"}