{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZDSZBD6DY6OAUMKIDKNS5INZRG","short_pith_number":"pith:ZDSZBD6D","schema_version":"1.0","canonical_sha256":"c8e5908fc3c79c0a31481a9b2ea1b9899aa97bef65204c02076c21abe303c455","source":{"kind":"arxiv","id":"1611.04021","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Video Descriptions to Learn Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Ching-Yao Chuang, Juan Carlos Niebles, Kuo-Hao Zeng, Min Sun, Tseng-Hung Chen, Yuan-Hong Liao","submitted_at":"2016-11-12T17:15:57Z","abstract_excerpt":"We propose a scalable approach to learn video-based question answering (QA): answer a \"free-form natural language question\" about a video content. Our approach automatically harvests a large number of videos and descriptions freely available online. Then, a large number of candidate QA pairs are automatically generated from descriptions rather than manually annotated. Next, we use these candidate QA pairs to train a number of video-based QA methods extended fromMN (Sukhbaatar et al. 2015), VQA (Antol et al. 2015), SA (Yao et al. 2015), SS (Venugopalan et al. 2015). In order to handle non-perfe"},"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":"1611.04021","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-12T17:15:57Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"1671daffeb5ad4166ef83c3a7c4c76e7f94823f300c518899fc76525aacff9a3","abstract_canon_sha256":"2b4585358825a97486a60360546bf138f7057ad7b08a6ae538f736b19454c033"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:47.207441Z","signature_b64":"9VGA1OTgUikG2T7yzOARsVkyMt/+D6DOe+1QXpQp6C9HnBNUjNdVrY8YCpnyQKNm6L76ukCeeqF86cgTF/E9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e5908fc3c79c0a31481a9b2ea1b9899aa97bef65204c02076c21abe303c455","last_reissued_at":"2026-05-18T00:54:47.206703Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:47.206703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Video Descriptions to Learn Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Ching-Yao Chuang, Juan Carlos Niebles, Kuo-Hao Zeng, Min Sun, Tseng-Hung Chen, Yuan-Hong Liao","submitted_at":"2016-11-12T17:15:57Z","abstract_excerpt":"We propose a scalable approach to learn video-based question answering (QA): answer a \"free-form natural language question\" about a video content. Our approach automatically harvests a large number of videos and descriptions freely available online. Then, a large number of candidate QA pairs are automatically generated from descriptions rather than manually annotated. Next, we use these candidate QA pairs to train a number of video-based QA methods extended fromMN (Sukhbaatar et al. 2015), VQA (Antol et al. 2015), SA (Yao et al. 2015), SS (Venugopalan et al. 2015). In order to handle non-perfe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04021","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":"1611.04021","created_at":"2026-05-18T00:54:47.206821+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.04021v2","created_at":"2026-05-18T00:54:47.206821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04021","created_at":"2026-05-18T00:54:47.206821+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDSZBD6DY6OA","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDSZBD6DY6OAUMKI","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDSZBD6D","created_at":"2026-05-18T12:30:53.716459+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/ZDSZBD6DY6OAUMKIDKNS5INZRG","json":"https://pith.science/pith/ZDSZBD6DY6OAUMKIDKNS5INZRG.json","graph_json":"https://pith.science/api/pith-number/ZDSZBD6DY6OAUMKIDKNS5INZRG/graph.json","events_json":"https://pith.science/api/pith-number/ZDSZBD6DY6OAUMKIDKNS5INZRG/events.json","paper":"https://pith.science/paper/ZDSZBD6D"},"agent_actions":{"view_html":"https://pith.science/pith/ZDSZBD6DY6OAUMKIDKNS5INZRG","download_json":"https://pith.science/pith/ZDSZBD6DY6OAUMKIDKNS5INZRG.json","view_paper":"https://pith.science/paper/ZDSZBD6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.04021&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDSZBD6DY6OAUMKIDKNS5INZRG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDSZBD6DY6OAUMKIDKNS5INZRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDSZBD6DY6OAUMKIDKNS5INZRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDSZBD6DY6OAUMKIDKNS5INZRG/action/storage_attestation","attest_author":"https://pith.science/pith/ZDSZBD6DY6OAUMKIDKNS5INZRG/action/author_attestation","sign_citation":"https://pith.science/pith/ZDSZBD6DY6OAUMKIDKNS5INZRG/action/citation_signature","submit_replication":"https://pith.science/pith/ZDSZBD6DY6OAUMKIDKNS5INZRG/action/replication_record"}},"created_at":"2026-05-18T00:54:47.206821+00:00","updated_at":"2026-05-18T00:54:47.206821+00:00"}