{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:3JFT2IHAGHMOPDO7WX4PL4TCWM","short_pith_number":"pith:3JFT2IHA","schema_version":"1.0","canonical_sha256":"da4b3d20e031d8e78ddfb5f8f5f262b32d442a2df82917c7d4e7d5b3e5023468","source":{"kind":"arxiv","id":"1511.04670","version":1},"attestation_state":"computed","paper":{"title":"Uncovering Temporal Context for Video Question and Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander G. Hauptmann, Linchao Zhu, Yi Yang, Zhongwen Xu","submitted_at":"2015-11-15T07:57:41Z","abstract_excerpt":"In this work, we introduce Video Question Answering in temporal domain to infer the past, describe the present and predict the future. We present an encoder-decoder approach using Recurrent Neural Networks to learn temporal structures of videos and introduce a dual-channel ranking loss to answer multiple-choice questions. We explore approaches for finer understanding of video content using question form of \"fill-in-the-blank\", and managed to collect 109,895 video clips with duration over 1,000 hours from TACoS, MPII-MD, MEDTest 14 datasets, while the corresponding 390,744 questions are generat"},"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":"1511.04670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-15T07:57:41Z","cross_cats_sorted":[],"title_canon_sha256":"e03a3783e4fd394acee0fd644392c308d59b7b4c1967e1ab2b7ce16d60b8f6e5","abstract_canon_sha256":"c5aca72c407d46fda7418f89e4c5907813c31df3dd92da8933f9bf765765442e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:52.067748Z","signature_b64":"op1nwWhRBdY2/Oh1RfN4Nc5xMP4E6Xw96OzQ8Ka4TXpg+MGLL8//ORHfUNgSSSK/MQzN7+oCYUS9JAXilKwVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da4b3d20e031d8e78ddfb5f8f5f262b32d442a2df82917c7d4e7d5b3e5023468","last_reissued_at":"2026-05-18T01:26:52.067014Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:52.067014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncovering Temporal Context for Video Question and Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander G. Hauptmann, Linchao Zhu, Yi Yang, Zhongwen Xu","submitted_at":"2015-11-15T07:57:41Z","abstract_excerpt":"In this work, we introduce Video Question Answering in temporal domain to infer the past, describe the present and predict the future. We present an encoder-decoder approach using Recurrent Neural Networks to learn temporal structures of videos and introduce a dual-channel ranking loss to answer multiple-choice questions. We explore approaches for finer understanding of video content using question form of \"fill-in-the-blank\", and managed to collect 109,895 video clips with duration over 1,000 hours from TACoS, MPII-MD, MEDTest 14 datasets, while the corresponding 390,744 questions are generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.04670","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":"1511.04670","created_at":"2026-05-18T01:26:52.067143+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.04670v1","created_at":"2026-05-18T01:26:52.067143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.04670","created_at":"2026-05-18T01:26:52.067143+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JFT2IHAGHMO","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JFT2IHAGHMOPDO7","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JFT2IHA","created_at":"2026-05-18T12:29:02.477457+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/3JFT2IHAGHMOPDO7WX4PL4TCWM","json":"https://pith.science/pith/3JFT2IHAGHMOPDO7WX4PL4TCWM.json","graph_json":"https://pith.science/api/pith-number/3JFT2IHAGHMOPDO7WX4PL4TCWM/graph.json","events_json":"https://pith.science/api/pith-number/3JFT2IHAGHMOPDO7WX4PL4TCWM/events.json","paper":"https://pith.science/paper/3JFT2IHA"},"agent_actions":{"view_html":"https://pith.science/pith/3JFT2IHAGHMOPDO7WX4PL4TCWM","download_json":"https://pith.science/pith/3JFT2IHAGHMOPDO7WX4PL4TCWM.json","view_paper":"https://pith.science/paper/3JFT2IHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.04670&json=true","fetch_graph":"https://pith.science/api/pith-number/3JFT2IHAGHMOPDO7WX4PL4TCWM/graph.json","fetch_events":"https://pith.science/api/pith-number/3JFT2IHAGHMOPDO7WX4PL4TCWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JFT2IHAGHMOPDO7WX4PL4TCWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JFT2IHAGHMOPDO7WX4PL4TCWM/action/storage_attestation","attest_author":"https://pith.science/pith/3JFT2IHAGHMOPDO7WX4PL4TCWM/action/author_attestation","sign_citation":"https://pith.science/pith/3JFT2IHAGHMOPDO7WX4PL4TCWM/action/citation_signature","submit_replication":"https://pith.science/pith/3JFT2IHAGHMOPDO7WX4PL4TCWM/action/replication_record"}},"created_at":"2026-05-18T01:26:52.067143+00:00","updated_at":"2026-05-18T01:26:52.067143+00:00"}