{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:273TWT26DRUQ4RVR2T77RKONY5","short_pith_number":"pith:273TWT26","schema_version":"1.0","canonical_sha256":"d7f73b4f5e1c690e46b1d4fff8a9cdc7619cc72a1af0d9508edaf6600862d80e","source":{"kind":"arxiv","id":"2205.04061","version":1},"attestation_state":"computed","paper":{"title":"Multilevel Hierarchical Network with Multiscale Sampling for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chongyang Wang, Min Peng, Xiang-Dong Zhou, Yuan Gao, Yu Shi","submitted_at":"2022-05-09T06:28:56Z","abstract_excerpt":"Video question answering (VideoQA) is challenging given its multimodal combination of visual understanding and natural language processing. While most existing approaches ignore the visual appearance-motion information at different temporal scales, it is unknown how to incorporate the multilevel processing capacity of a deep learning model with such multiscale information. Targeting these issues, this paper proposes a novel Multilevel Hierarchical Network (MHN) with multiscale sampling for VideoQA. MHN comprises two modules, namely Recurrent Multimodal Interaction (RMI) and Parallel Visual Rea"},"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":"2205.04061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-09T06:28:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a805b8669e6cb1bd8e9d48cbe05be69b257bd9ae0874a3e59d8d67a318b9ae0b","abstract_canon_sha256":"edd89de4d73432d49fd8c3587d4dad55b260202d8aa413e150cdfd60f12a3bb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:20.909632Z","signature_b64":"0WibL6UIvOBrwwOarqalDDuTyv7UeVo2NnVndIrdFTM0NsvqQReyvyS8jCWmP5zEUb3Q3BpkfCzA+0NkjGlVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7f73b4f5e1c690e46b1d4fff8a9cdc7619cc72a1af0d9508edaf6600862d80e","last_reissued_at":"2026-07-05T04:21:20.909183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:20.909183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilevel Hierarchical Network with Multiscale Sampling for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chongyang Wang, Min Peng, Xiang-Dong Zhou, Yuan Gao, Yu Shi","submitted_at":"2022-05-09T06:28:56Z","abstract_excerpt":"Video question answering (VideoQA) is challenging given its multimodal combination of visual understanding and natural language processing. While most existing approaches ignore the visual appearance-motion information at different temporal scales, it is unknown how to incorporate the multilevel processing capacity of a deep learning model with such multiscale information. Targeting these issues, this paper proposes a novel Multilevel Hierarchical Network (MHN) with multiscale sampling for VideoQA. MHN comprises two modules, namely Recurrent Multimodal Interaction (RMI) and Parallel Visual Rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04061","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.04061/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2205.04061","created_at":"2026-07-05T04:21:20.909246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.04061v1","created_at":"2026-07-05T04:21:20.909246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04061","created_at":"2026-07-05T04:21:20.909246+00:00"},{"alias_kind":"pith_short_12","alias_value":"273TWT26DRUQ","created_at":"2026-07-05T04:21:20.909246+00:00"},{"alias_kind":"pith_short_16","alias_value":"273TWT26DRUQ4RVR","created_at":"2026-07-05T04:21:20.909246+00:00"},{"alias_kind":"pith_short_8","alias_value":"273TWT26","created_at":"2026-07-05T04:21:20.909246+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/273TWT26DRUQ4RVR2T77RKONY5","json":"https://pith.science/pith/273TWT26DRUQ4RVR2T77RKONY5.json","graph_json":"https://pith.science/api/pith-number/273TWT26DRUQ4RVR2T77RKONY5/graph.json","events_json":"https://pith.science/api/pith-number/273TWT26DRUQ4RVR2T77RKONY5/events.json","paper":"https://pith.science/paper/273TWT26"},"agent_actions":{"view_html":"https://pith.science/pith/273TWT26DRUQ4RVR2T77RKONY5","download_json":"https://pith.science/pith/273TWT26DRUQ4RVR2T77RKONY5.json","view_paper":"https://pith.science/paper/273TWT26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.04061&json=true","fetch_graph":"https://pith.science/api/pith-number/273TWT26DRUQ4RVR2T77RKONY5/graph.json","fetch_events":"https://pith.science/api/pith-number/273TWT26DRUQ4RVR2T77RKONY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/273TWT26DRUQ4RVR2T77RKONY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/273TWT26DRUQ4RVR2T77RKONY5/action/storage_attestation","attest_author":"https://pith.science/pith/273TWT26DRUQ4RVR2T77RKONY5/action/author_attestation","sign_citation":"https://pith.science/pith/273TWT26DRUQ4RVR2T77RKONY5/action/citation_signature","submit_replication":"https://pith.science/pith/273TWT26DRUQ4RVR2T77RKONY5/action/replication_record"}},"created_at":"2026-07-05T04:21:20.909246+00:00","updated_at":"2026-07-05T04:21:20.909246+00:00"}