{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5YXRU5VMMX2YEPA2YLW2IXMZ6N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c85e9066af8ab8ba20445dd8d6ef9a9d31dff7b5d07021b4550a882d6451c40d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-08T21:10:16Z","title_canon_sha256":"1ab76a314d63b990bd057fba57a0328f0091ac68c06e5a224c105033fbcb96c4"},"schema_version":"1.0","source":{"id":"1904.04357","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04357","created_at":"2026-05-17T23:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04357v1","created_at":"2026-05-17T23:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04357","created_at":"2026-05-17T23:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"5YXRU5VMMX2Y","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5YXRU5VMMX2YEPA2","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5YXRU5VM","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:cae292d083dc342dcb3f18a3083422f7798cd0c1abf72841835166b9a6b4d969","target":"graph","created_at":"2026-05-17T23:48:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion features; 2) a redesigned question memory which helps understand the complex semantics of question and highlights queried subjects; and 3) a new multimodal fusion layer which performs multi-step reasoning by attending to relevant visual and textual hints with self-updated attention. Our VideoQA model firstly generates the global context-aware visual and tex","authors_text":"Chenyou Fan, Chi Zhang, Heng Huang, Shu Zhang, Wensheng Wang, Xiaofan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-08T21:10:16Z","title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04357","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b580e6b5ac56c97dceafe553919f321533bfcea356c66d4891be62df0c0361fc","target":"record","created_at":"2026-05-17T23:48:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c85e9066af8ab8ba20445dd8d6ef9a9d31dff7b5d07021b4550a882d6451c40d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-08T21:10:16Z","title_canon_sha256":"1ab76a314d63b990bd057fba57a0328f0091ac68c06e5a224c105033fbcb96c4"},"schema_version":"1.0","source":{"id":"1904.04357","kind":"arxiv","version":1}},"canonical_sha256":"ee2f1a76ac65f5823c1ac2eda45d99f36d0cc47597375da0a19179c01b570a11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee2f1a76ac65f5823c1ac2eda45d99f36d0cc47597375da0a19179c01b570a11","first_computed_at":"2026-05-17T23:48:59.202494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:59.202494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rTsJ58OAIKK/FJ8wOxzt9096lR3qDMSUi/OArGfoCCWo1drREgrPFwW5hGUS40i/c9kD5GUXdVYmRRH9p4J+DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:59.202892Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04357","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b580e6b5ac56c97dceafe553919f321533bfcea356c66d4891be62df0c0361fc","sha256:cae292d083dc342dcb3f18a3083422f7798cd0c1abf72841835166b9a6b4d969"],"state_sha256":"618e4c29cefad1d60c15c3ef099ec73e5a67344518282ccee771158b7ffdb4a5"}