{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GK43VP2RM2QUUCDWM3VIH4Z6QP","short_pith_number":"pith:GK43VP2R","schema_version":"1.0","canonical_sha256":"32b9babf5166a14a087666ea83f33e83e6e87d30bb97d11435a3189bbffc2c18","source":{"kind":"arxiv","id":"1801.07853","version":1},"attestation_state":"computed","paper":{"title":"Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charless Fowlkes, Liangjian Chen, Limin Wang, Xiaohui Xie, Xiaoyi Liu, Yu Qiao, Zhe Wang","submitted_at":"2018-01-24T03:58:51Z","abstract_excerpt":"Visual question answering (VQA) is of significant interest due to its potential to be a strong test of image understanding systems and to probe the connection between language and vision. Despite much recent progress, general VQA is far from a solved problem. In this paper, we focus on the VQA multiple-choice task, and provide some good practices for designing an effective VQA model that can capture language-vision interactions and perform joint reasoning. We explore mechanisms of incorporating part-of-speech (POS) tag guided attention, convolutional n-grams, triplet attention interactions bet"},"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":"1801.07853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T03:58:51Z","cross_cats_sorted":[],"title_canon_sha256":"0fcce05340cc7b8174e5f900f856a54002b80737ae4c75615917cda73c8f26e7","abstract_canon_sha256":"10011ef3bf218fce7ce21486a1ebba73fccaee7c94f79dc6aaeb362b542ad953"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:10.674246Z","signature_b64":"OZF0j8GaX9lz4j0TX9C6hLcqfsk12AzjLJAn6ZumNNydbOkPRWxczgiZbV83GQLkUl3wtSKa+NUF//fykNS5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32b9babf5166a14a087666ea83f33e83e6e87d30bb97d11435a3189bbffc2c18","last_reissued_at":"2026-05-18T00:25:10.673760Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:10.673760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charless Fowlkes, Liangjian Chen, Limin Wang, Xiaohui Xie, Xiaoyi Liu, Yu Qiao, Zhe Wang","submitted_at":"2018-01-24T03:58:51Z","abstract_excerpt":"Visual question answering (VQA) is of significant interest due to its potential to be a strong test of image understanding systems and to probe the connection between language and vision. Despite much recent progress, general VQA is far from a solved problem. In this paper, we focus on the VQA multiple-choice task, and provide some good practices for designing an effective VQA model that can capture language-vision interactions and perform joint reasoning. We explore mechanisms of incorporating part-of-speech (POS) tag guided attention, convolutional n-grams, triplet attention interactions bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07853","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":"1801.07853","created_at":"2026-05-18T00:25:10.673832+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.07853v1","created_at":"2026-05-18T00:25:10.673832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07853","created_at":"2026-05-18T00:25:10.673832+00:00"},{"alias_kind":"pith_short_12","alias_value":"GK43VP2RM2QU","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GK43VP2RM2QUUCDW","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GK43VP2R","created_at":"2026-05-18T12:32:25.280505+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/GK43VP2RM2QUUCDWM3VIH4Z6QP","json":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP.json","graph_json":"https://pith.science/api/pith-number/GK43VP2RM2QUUCDWM3VIH4Z6QP/graph.json","events_json":"https://pith.science/api/pith-number/GK43VP2RM2QUUCDWM3VIH4Z6QP/events.json","paper":"https://pith.science/paper/GK43VP2R"},"agent_actions":{"view_html":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP","download_json":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP.json","view_paper":"https://pith.science/paper/GK43VP2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.07853&json=true","fetch_graph":"https://pith.science/api/pith-number/GK43VP2RM2QUUCDWM3VIH4Z6QP/graph.json","fetch_events":"https://pith.science/api/pith-number/GK43VP2RM2QUUCDWM3VIH4Z6QP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/action/storage_attestation","attest_author":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/action/author_attestation","sign_citation":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/action/citation_signature","submit_replication":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/action/replication_record"}},"created_at":"2026-05-18T00:25:10.673832+00:00","updated_at":"2026-05-18T00:25:10.673832+00:00"}