{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:625KHH53DC2DQ2WEHT4HSFXOQB","short_pith_number":"pith:625KHH53","schema_version":"1.0","canonical_sha256":"f6baa39fbb18b4386ac43cf87916ee80690b7db6285155ea95afa8ce3370ed39","source":{"kind":"arxiv","id":"1711.04323","version":1},"attestation_state":"computed","paper":{"title":"High-Order Attention Models for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander G. Schwing, Idan Schwartz, Tamir Hazan","submitted_at":"2017-11-12T17:30:05Z","abstract_excerpt":"The quest for algorithms that enable cognitive abilities is an important part of machine learning. A common trait in many recently investigated cognitive-like tasks is that they take into account different data modalities, such as visual and textual input. In this paper we propose a novel and generally applicable form of attention mechanism that learns high-order correlations between various data modalities. We show that high-order correlations effectively direct the appropriate attention to the relevant elements in the different data modalities that are required to solve the joint task. We de"},"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":"1711.04323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-12T17:30:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e965bf2efc6e9325b08b8c56f5ef92d2ae51579b3e0ad12d4f0bdb8480463525","abstract_canon_sha256":"2e121a0b3f4a0b404dfc1acfe26fa50abb530b3dd8463b7ffce5d3167e78cfd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:39.424205Z","signature_b64":"i9P/8eGlAfoK3V6QdrfVMuQfySXpYe1CaDGjUQ5w7wG5AZ0WWiQ2NI0fQ8crWFSi+odNqIQ8uob8qqQqBnxICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6baa39fbb18b4386ac43cf87916ee80690b7db6285155ea95afa8ce3370ed39","last_reissued_at":"2026-05-18T00:30:39.423621Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:39.423621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Order Attention Models for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander G. Schwing, Idan Schwartz, Tamir Hazan","submitted_at":"2017-11-12T17:30:05Z","abstract_excerpt":"The quest for algorithms that enable cognitive abilities is an important part of machine learning. A common trait in many recently investigated cognitive-like tasks is that they take into account different data modalities, such as visual and textual input. In this paper we propose a novel and generally applicable form of attention mechanism that learns high-order correlations between various data modalities. We show that high-order correlations effectively direct the appropriate attention to the relevant elements in the different data modalities that are required to solve the joint task. We de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04323","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":"1711.04323","created_at":"2026-05-18T00:30:39.423712+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04323v1","created_at":"2026-05-18T00:30:39.423712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04323","created_at":"2026-05-18T00:30:39.423712+00:00"},{"alias_kind":"pith_short_12","alias_value":"625KHH53DC2D","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"625KHH53DC2DQ2WE","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"625KHH53","created_at":"2026-05-18T12:31:03.183658+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/625KHH53DC2DQ2WEHT4HSFXOQB","json":"https://pith.science/pith/625KHH53DC2DQ2WEHT4HSFXOQB.json","graph_json":"https://pith.science/api/pith-number/625KHH53DC2DQ2WEHT4HSFXOQB/graph.json","events_json":"https://pith.science/api/pith-number/625KHH53DC2DQ2WEHT4HSFXOQB/events.json","paper":"https://pith.science/paper/625KHH53"},"agent_actions":{"view_html":"https://pith.science/pith/625KHH53DC2DQ2WEHT4HSFXOQB","download_json":"https://pith.science/pith/625KHH53DC2DQ2WEHT4HSFXOQB.json","view_paper":"https://pith.science/paper/625KHH53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04323&json=true","fetch_graph":"https://pith.science/api/pith-number/625KHH53DC2DQ2WEHT4HSFXOQB/graph.json","fetch_events":"https://pith.science/api/pith-number/625KHH53DC2DQ2WEHT4HSFXOQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/625KHH53DC2DQ2WEHT4HSFXOQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/625KHH53DC2DQ2WEHT4HSFXOQB/action/storage_attestation","attest_author":"https://pith.science/pith/625KHH53DC2DQ2WEHT4HSFXOQB/action/author_attestation","sign_citation":"https://pith.science/pith/625KHH53DC2DQ2WEHT4HSFXOQB/action/citation_signature","submit_replication":"https://pith.science/pith/625KHH53DC2DQ2WEHT4HSFXOQB/action/replication_record"}},"created_at":"2026-05-18T00:30:39.423712+00:00","updated_at":"2026-05-18T00:30:39.423712+00:00"}