{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QKWBILCT3GSPVLFGVZ5WV5K6BU","short_pith_number":"pith:QKWBILCT","schema_version":"1.0","canonical_sha256":"82ac142c53d9a4faaca6ae7b6af55e0d09facb2476b43a4c787bb3b703477ca0","source":{"kind":"arxiv","id":"1905.13540","version":1},"attestation_state":"computed","paper":{"title":"Gaining Extra Supervision via Multi-task learning for Multi-Modal Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Chang D. Yoo, Junyeong Kim, Kyungsu Kim, Minuk Ma, Sungjin Kim","submitted_at":"2019-05-28T01:46:20Z","abstract_excerpt":"This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering. Multi-modal video question answering is an important task that aims at the joint understanding of vision and language. However, establishing large scale dataset for multi-modal video question answering is expensive and the existing benchmarks are relatively small to provide sufficient supervision. To overcome this challenge, this paper proposes a multi-task learning method which is composed of three main components: (1) multi-modal video question answering network that answe"},"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":"1905.13540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-28T01:46:20Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a8701c4ae060ef754a9da7e2e363dfb8d8e7dac66b03df0c0bc1cb867f53c958","abstract_canon_sha256":"09767e165cb511b62a5384ed98c4ab13cb8eafa5cd461a96e2175f9f9735f1dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:34.637159Z","signature_b64":"q00w5aNl6HOSrWKgzbIxNEIfbljJrXcDeOtIYUrx5CX1bM2Jhs8qDWxO+r3fEaTAhl4HoW3k9hzEoSMD1ZCABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82ac142c53d9a4faaca6ae7b6af55e0d09facb2476b43a4c787bb3b703477ca0","last_reissued_at":"2026-05-17T23:44:34.636560Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:34.636560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaining Extra Supervision via Multi-task learning for Multi-Modal Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Chang D. Yoo, Junyeong Kim, Kyungsu Kim, Minuk Ma, Sungjin Kim","submitted_at":"2019-05-28T01:46:20Z","abstract_excerpt":"This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering. Multi-modal video question answering is an important task that aims at the joint understanding of vision and language. However, establishing large scale dataset for multi-modal video question answering is expensive and the existing benchmarks are relatively small to provide sufficient supervision. To overcome this challenge, this paper proposes a multi-task learning method which is composed of three main components: (1) multi-modal video question answering network that answe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13540","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":"1905.13540","created_at":"2026-05-17T23:44:34.636671+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13540v1","created_at":"2026-05-17T23:44:34.636671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13540","created_at":"2026-05-17T23:44:34.636671+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKWBILCT3GSP","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKWBILCT3GSPVLFG","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKWBILCT","created_at":"2026-05-18T12:33:27.125529+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/QKWBILCT3GSPVLFGVZ5WV5K6BU","json":"https://pith.science/pith/QKWBILCT3GSPVLFGVZ5WV5K6BU.json","graph_json":"https://pith.science/api/pith-number/QKWBILCT3GSPVLFGVZ5WV5K6BU/graph.json","events_json":"https://pith.science/api/pith-number/QKWBILCT3GSPVLFGVZ5WV5K6BU/events.json","paper":"https://pith.science/paper/QKWBILCT"},"agent_actions":{"view_html":"https://pith.science/pith/QKWBILCT3GSPVLFGVZ5WV5K6BU","download_json":"https://pith.science/pith/QKWBILCT3GSPVLFGVZ5WV5K6BU.json","view_paper":"https://pith.science/paper/QKWBILCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13540&json=true","fetch_graph":"https://pith.science/api/pith-number/QKWBILCT3GSPVLFGVZ5WV5K6BU/graph.json","fetch_events":"https://pith.science/api/pith-number/QKWBILCT3GSPVLFGVZ5WV5K6BU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKWBILCT3GSPVLFGVZ5WV5K6BU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKWBILCT3GSPVLFGVZ5WV5K6BU/action/storage_attestation","attest_author":"https://pith.science/pith/QKWBILCT3GSPVLFGVZ5WV5K6BU/action/author_attestation","sign_citation":"https://pith.science/pith/QKWBILCT3GSPVLFGVZ5WV5K6BU/action/citation_signature","submit_replication":"https://pith.science/pith/QKWBILCT3GSPVLFGVZ5WV5K6BU/action/replication_record"}},"created_at":"2026-05-17T23:44:34.636671+00:00","updated_at":"2026-05-17T23:44:34.636671+00:00"}