{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CTCC7UVNTMQMIECRPESE4B3RVS","short_pith_number":"pith:CTCC7UVN","schema_version":"1.0","canonical_sha256":"14c42fd2ad9b20c4105179244e0771ac970da1798f36ef8baa8f7570a09e28a7","source":{"kind":"arxiv","id":"1808.02559","version":1},"attestation_state":"computed","paper":{"title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gunhee Kim, Jongseok Kim, Youngjae Yu","submitted_at":"2018-08-07T21:33:37Z","abstract_excerpt":"We present an approach named JSFusion (Joint Sequence Fusion) that can measure semantic similarity between any pairs of multimodal sequence data (e.g. a video clip and a language sentence). Our multimodal matching network consists of two key components. First, the Joint Semantic Tensor composes a dense pairwise representation of two sequence data into a 3D tensor. Then, the Convolutional Hierarchical Decoder computes their similarity score by discovering hidden hierarchical matches between the two sequence modalities. Both modules leverage hierarchical attention mechanisms that learn to promot"},"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":"1808.02559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-07T21:33:37Z","cross_cats_sorted":[],"title_canon_sha256":"0181c4f60fd28a820d7dd5a726a4e5c6b6de8a3b756451ca1626ad6c465d871e","abstract_canon_sha256":"5820497671f32344368feb28bbeb4d55efd904e17e3043196d7e04e59289fe91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:35.031920Z","signature_b64":"qj9k41RTxds5ZuqcfXqmt4CbvJ03rO4btVH5/eAk6iF4RZLK+XwO5BzEWCNoVQZsATr9kIojZJ7lNtOyQCWEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14c42fd2ad9b20c4105179244e0771ac970da1798f36ef8baa8f7570a09e28a7","last_reissued_at":"2026-05-18T00:08:35.031379Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:35.031379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gunhee Kim, Jongseok Kim, Youngjae Yu","submitted_at":"2018-08-07T21:33:37Z","abstract_excerpt":"We present an approach named JSFusion (Joint Sequence Fusion) that can measure semantic similarity between any pairs of multimodal sequence data (e.g. a video clip and a language sentence). Our multimodal matching network consists of two key components. First, the Joint Semantic Tensor composes a dense pairwise representation of two sequence data into a 3D tensor. Then, the Convolutional Hierarchical Decoder computes their similarity score by discovering hidden hierarchical matches between the two sequence modalities. Both modules leverage hierarchical attention mechanisms that learn to promot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.02559","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":"1808.02559","created_at":"2026-05-18T00:08:35.031463+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.02559v1","created_at":"2026-05-18T00:08:35.031463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.02559","created_at":"2026-05-18T00:08:35.031463+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTCC7UVNTMQM","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTCC7UVNTMQMIECR","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTCC7UVN","created_at":"2026-05-18T12:32:19.392346+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/CTCC7UVNTMQMIECRPESE4B3RVS","json":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS.json","graph_json":"https://pith.science/api/pith-number/CTCC7UVNTMQMIECRPESE4B3RVS/graph.json","events_json":"https://pith.science/api/pith-number/CTCC7UVNTMQMIECRPESE4B3RVS/events.json","paper":"https://pith.science/paper/CTCC7UVN"},"agent_actions":{"view_html":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS","download_json":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS.json","view_paper":"https://pith.science/paper/CTCC7UVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.02559&json=true","fetch_graph":"https://pith.science/api/pith-number/CTCC7UVNTMQMIECRPESE4B3RVS/graph.json","fetch_events":"https://pith.science/api/pith-number/CTCC7UVNTMQMIECRPESE4B3RVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS/action/storage_attestation","attest_author":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS/action/author_attestation","sign_citation":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS/action/citation_signature","submit_replication":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS/action/replication_record"}},"created_at":"2026-05-18T00:08:35.031463+00:00","updated_at":"2026-05-18T00:08:35.031463+00:00"}