{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5AEUUB7SXLRUQM6HM3DK7ZAFAG","short_pith_number":"pith:5AEUUB7S","schema_version":"1.0","canonical_sha256":"e8094a07f2bae34833c766c6afe40501bb50ecc1b15255a099fc02f674071824","source":{"kind":"arxiv","id":"1902.00038","version":2},"attestation_state":"computed","paper":{"title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hedi Ben-younes, Matthieu Cord, Nicolas Thome, R\\'emi Cadene","submitted_at":"2019-01-31T19:10:14Z","abstract_excerpt":"Multimodal representation learning is gaining more and more interest within the deep learning community. While bilinear models provide an interesting framework to find subtle combination of modalities, their number of parameters grows quadratically with the input dimensions, making their practical implementation within classical deep learning pipelines challenging. In this paper, we introduce BLOCK, a new multimodal fusion based on the block-superdiagonal tensor decomposition. It leverages the notion of block-term ranks, which generalizes both concepts of rank and mode ranks for tensors, alrea"},"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":"1902.00038","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-31T19:10:14Z","cross_cats_sorted":[],"title_canon_sha256":"5efca41795b87d892f11cb272e488d7bf0cb05c3f6486495892bc6a5f680aabc","abstract_canon_sha256":"3da7524e235b50fab1e1f5710fca2f4c7c5f7761f8ec169057b9cb4bff37af5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:15.029461Z","signature_b64":"kAn3CDSJjk2mXSFuQpW+g0IDBz+fJlmOb+PvEJOyII2IvmztCcJX0eYrXGAEWC0DWZdFDoNa3Rk0KXP33ENICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8094a07f2bae34833c766c6afe40501bb50ecc1b15255a099fc02f674071824","last_reissued_at":"2026-05-17T23:54:15.028997Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:15.028997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hedi Ben-younes, Matthieu Cord, Nicolas Thome, R\\'emi Cadene","submitted_at":"2019-01-31T19:10:14Z","abstract_excerpt":"Multimodal representation learning is gaining more and more interest within the deep learning community. While bilinear models provide an interesting framework to find subtle combination of modalities, their number of parameters grows quadratically with the input dimensions, making their practical implementation within classical deep learning pipelines challenging. In this paper, we introduce BLOCK, a new multimodal fusion based on the block-superdiagonal tensor decomposition. It leverages the notion of block-term ranks, which generalizes both concepts of rank and mode ranks for tensors, alrea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00038","kind":"arxiv","version":2},"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":"1902.00038","created_at":"2026-05-17T23:54:15.029069+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00038v2","created_at":"2026-05-17T23:54:15.029069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00038","created_at":"2026-05-17T23:54:15.029069+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AEUUB7SXLRU","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AEUUB7SXLRUQM6H","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AEUUB7S","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11150","citing_title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AEUUB7SXLRUQM6HM3DK7ZAFAG","json":"https://pith.science/pith/5AEUUB7SXLRUQM6HM3DK7ZAFAG.json","graph_json":"https://pith.science/api/pith-number/5AEUUB7SXLRUQM6HM3DK7ZAFAG/graph.json","events_json":"https://pith.science/api/pith-number/5AEUUB7SXLRUQM6HM3DK7ZAFAG/events.json","paper":"https://pith.science/paper/5AEUUB7S"},"agent_actions":{"view_html":"https://pith.science/pith/5AEUUB7SXLRUQM6HM3DK7ZAFAG","download_json":"https://pith.science/pith/5AEUUB7SXLRUQM6HM3DK7ZAFAG.json","view_paper":"https://pith.science/paper/5AEUUB7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00038&json=true","fetch_graph":"https://pith.science/api/pith-number/5AEUUB7SXLRUQM6HM3DK7ZAFAG/graph.json","fetch_events":"https://pith.science/api/pith-number/5AEUUB7SXLRUQM6HM3DK7ZAFAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AEUUB7SXLRUQM6HM3DK7ZAFAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AEUUB7SXLRUQM6HM3DK7ZAFAG/action/storage_attestation","attest_author":"https://pith.science/pith/5AEUUB7SXLRUQM6HM3DK7ZAFAG/action/author_attestation","sign_citation":"https://pith.science/pith/5AEUUB7SXLRUQM6HM3DK7ZAFAG/action/citation_signature","submit_replication":"https://pith.science/pith/5AEUUB7SXLRUQM6HM3DK7ZAFAG/action/replication_record"}},"created_at":"2026-05-17T23:54:15.029069+00:00","updated_at":"2026-05-17T23:54:15.029069+00:00"}