{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2KCRIT4B52WY52BAPQ7X7HOCMU","short_pith_number":"pith:2KCRIT4B","schema_version":"1.0","canonical_sha256":"d285144f81eead8ee8207c3f7f9dc2652d640c9b0961e38e10e31b54ec72aff2","source":{"kind":"arxiv","id":"1803.10906","version":1},"attestation_state":"computed","paper":{"title":"Motion-Appearance Co-Memory Networks for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiyang Gao, Kan Chen, Ram Nevatia, Runzhou Ge","submitted_at":"2018-03-29T02:47:49Z","abstract_excerpt":"Video Question Answering (QA) is an important task in understanding video temporal structure. We observe that there are three unique attributes of video QA compared with image QA: (1) it deals with long sequences of images containing richer information not only in quantity but also in variety; (2) motion and appearance information are usually correlated with each other and able to provide useful attention cues to the other; (3) different questions require different number of frames to infer the answer. Based these observations, we propose a motion-appearance comemory network for video QA. Our "},"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":"1803.10906","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-29T02:47:49Z","cross_cats_sorted":[],"title_canon_sha256":"1d8188e4b4e2e4c01f1153423616a038ba9afdc5c3ad11a9089994fcab6ace33","abstract_canon_sha256":"e5213adc8b905d185086a95c95c5df395dfded2b81eaead70280153a9f7a06bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:49.835571Z","signature_b64":"fZCef4QKXTOW88CimWWbLQ9U342SEbecfr/47SkOtzX7sP6E06+j6uR4TJYH6CUzYvBHEgwBJGTog2dOfErqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d285144f81eead8ee8207c3f7f9dc2652d640c9b0961e38e10e31b54ec72aff2","last_reissued_at":"2026-05-18T00:19:49.834955Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:49.834955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motion-Appearance Co-Memory Networks for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiyang Gao, Kan Chen, Ram Nevatia, Runzhou Ge","submitted_at":"2018-03-29T02:47:49Z","abstract_excerpt":"Video Question Answering (QA) is an important task in understanding video temporal structure. We observe that there are three unique attributes of video QA compared with image QA: (1) it deals with long sequences of images containing richer information not only in quantity but also in variety; (2) motion and appearance information are usually correlated with each other and able to provide useful attention cues to the other; (3) different questions require different number of frames to infer the answer. Based these observations, we propose a motion-appearance comemory network for video QA. Our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10906","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":"1803.10906","created_at":"2026-05-18T00:19:49.835035+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.10906v1","created_at":"2026-05-18T00:19:49.835035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10906","created_at":"2026-05-18T00:19:49.835035+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KCRIT4B52WY","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KCRIT4B52WY52BA","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KCRIT4B","created_at":"2026-05-18T12:32:02.567920+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/2KCRIT4B52WY52BAPQ7X7HOCMU","json":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU.json","graph_json":"https://pith.science/api/pith-number/2KCRIT4B52WY52BAPQ7X7HOCMU/graph.json","events_json":"https://pith.science/api/pith-number/2KCRIT4B52WY52BAPQ7X7HOCMU/events.json","paper":"https://pith.science/paper/2KCRIT4B"},"agent_actions":{"view_html":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU","download_json":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU.json","view_paper":"https://pith.science/paper/2KCRIT4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.10906&json=true","fetch_graph":"https://pith.science/api/pith-number/2KCRIT4B52WY52BAPQ7X7HOCMU/graph.json","fetch_events":"https://pith.science/api/pith-number/2KCRIT4B52WY52BAPQ7X7HOCMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/action/storage_attestation","attest_author":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/action/author_attestation","sign_citation":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/action/citation_signature","submit_replication":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/action/replication_record"}},"created_at":"2026-05-18T00:19:49.835035+00:00","updated_at":"2026-05-18T00:19:49.835035+00:00"}