{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VG7M6665CZXL5XX53IKVG63W63","short_pith_number":"pith:VG7M6665","schema_version":"1.0","canonical_sha256":"a9becf7bdd166ebedefdda15537b76f6d36f8bc220cf5879598ec41fdc98863d","source":{"kind":"arxiv","id":"1712.06228","version":1},"attestation_state":"computed","paper":{"title":"Visual Explanations from Hadamard Product in Multimodal Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Byoung-Tak Zhang, Jin-Hwa Kim","submitted_at":"2017-12-18T02:37:20Z","abstract_excerpt":"The visual explanation of learned representation of models helps to understand the fundamentals of learning. The attentional models of previous works used to visualize the attended regions over an image or text using their learned weights to confirm their intended mechanism. Kim et al. (2016) show that the Hadamard product in multimodal deep networks, which is well-known for the joint function of visual question answering tasks, implicitly performs an attentional mechanism for visual inputs. In this work, we extend their work to show that the Hadamard product in multimodal deep networks perfor"},"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":"1712.06228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T02:37:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fbfc4053ae661e0283d7b812bc4f98c597113b70afac008764b040c3bc9a56c6","abstract_canon_sha256":"762ace571eb047c2ddecd55f731b4143407a9907c6581530cca716c549fec380"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:50.798665Z","signature_b64":"b/RkxUNBKQhf7ZqbaGjF6WHDquXzy+NoeMA2ldHAtFW86hSdds1O6yQQ7w43Wd166Sx0tJD451ixBM2k0IZuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9becf7bdd166ebedefdda15537b76f6d36f8bc220cf5879598ec41fdc98863d","last_reissued_at":"2026-05-18T00:27:50.798201Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:50.798201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Explanations from Hadamard Product in Multimodal Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Byoung-Tak Zhang, Jin-Hwa Kim","submitted_at":"2017-12-18T02:37:20Z","abstract_excerpt":"The visual explanation of learned representation of models helps to understand the fundamentals of learning. The attentional models of previous works used to visualize the attended regions over an image or text using their learned weights to confirm their intended mechanism. Kim et al. (2016) show that the Hadamard product in multimodal deep networks, which is well-known for the joint function of visual question answering tasks, implicitly performs an attentional mechanism for visual inputs. In this work, we extend their work to show that the Hadamard product in multimodal deep networks perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06228","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":"1712.06228","created_at":"2026-05-18T00:27:50.798270+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.06228v1","created_at":"2026-05-18T00:27:50.798270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06228","created_at":"2026-05-18T00:27:50.798270+00:00"},{"alias_kind":"pith_short_12","alias_value":"VG7M6665CZXL","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VG7M6665CZXL5XX5","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VG7M6665","created_at":"2026-05-18T12:31:49.984773+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/VG7M6665CZXL5XX53IKVG63W63","json":"https://pith.science/pith/VG7M6665CZXL5XX53IKVG63W63.json","graph_json":"https://pith.science/api/pith-number/VG7M6665CZXL5XX53IKVG63W63/graph.json","events_json":"https://pith.science/api/pith-number/VG7M6665CZXL5XX53IKVG63W63/events.json","paper":"https://pith.science/paper/VG7M6665"},"agent_actions":{"view_html":"https://pith.science/pith/VG7M6665CZXL5XX53IKVG63W63","download_json":"https://pith.science/pith/VG7M6665CZXL5XX53IKVG63W63.json","view_paper":"https://pith.science/paper/VG7M6665","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.06228&json=true","fetch_graph":"https://pith.science/api/pith-number/VG7M6665CZXL5XX53IKVG63W63/graph.json","fetch_events":"https://pith.science/api/pith-number/VG7M6665CZXL5XX53IKVG63W63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VG7M6665CZXL5XX53IKVG63W63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VG7M6665CZXL5XX53IKVG63W63/action/storage_attestation","attest_author":"https://pith.science/pith/VG7M6665CZXL5XX53IKVG63W63/action/author_attestation","sign_citation":"https://pith.science/pith/VG7M6665CZXL5XX53IKVG63W63/action/citation_signature","submit_replication":"https://pith.science/pith/VG7M6665CZXL5XX53IKVG63W63/action/replication_record"}},"created_at":"2026-05-18T00:27:50.798270+00:00","updated_at":"2026-05-18T00:27:50.798270+00:00"}