{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A4QSUGFH3V7CJUP5EUGDR3UTGF","short_pith_number":"pith:A4QSUGFH","schema_version":"1.0","canonical_sha256":"07212a18a7dd7e24d1fd250c38ee933179fd352ea5db745172a0a2f6c7c62877","source":{"kind":"arxiv","id":"2302.02136","version":2},"attestation_state":"computed","paper":{"title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyang Wang, Min Peng, Xiang-Dong Zhou, Yu Shi","submitted_at":"2023-02-04T09:14:18Z","abstract_excerpt":"This paper presents a new method for end-to-end Video Question Answering (VideoQA), aside from the current popularity of using large-scale pre-training with huge feature extractors. We achieve this with a pyramidal multimodal transformer (PMT) model, which simply incorporates a learnable word embedding layer, a few convolutional and transformer layers. We use the anisotropic pyramid to fulfill video-language interactions across different spatio-temporal scales. In addition to the canonical pyramid, which includes both bottom-up and top-down pathways with lateral connections, novel strategies a"},"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":"2302.02136","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-04T09:14:18Z","cross_cats_sorted":[],"title_canon_sha256":"c20d6b5db0d49d66e317f0bce431ae1c8c08b8124047a8401ce95c70370d9e90","abstract_canon_sha256":"5b6ab4b06f554da013ea70a15551d8d5a41900ca3509ba6598338f3259688f79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:05.743060Z","signature_b64":"zHqmFlta90ZqLLKDqMFFiQ2je4aPO7FPOYAQdy92rPBloLPYj90c04tUBNo/n+HaPVAXiXrW4xD2+4uRiotgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07212a18a7dd7e24d1fd250c38ee933179fd352ea5db745172a0a2f6c7c62877","last_reissued_at":"2026-07-05T05:48:05.742621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:05.742621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyang Wang, Min Peng, Xiang-Dong Zhou, Yu Shi","submitted_at":"2023-02-04T09:14:18Z","abstract_excerpt":"This paper presents a new method for end-to-end Video Question Answering (VideoQA), aside from the current popularity of using large-scale pre-training with huge feature extractors. We achieve this with a pyramidal multimodal transformer (PMT) model, which simply incorporates a learnable word embedding layer, a few convolutional and transformer layers. We use the anisotropic pyramid to fulfill video-language interactions across different spatio-temporal scales. In addition to the canonical pyramid, which includes both bottom-up and top-down pathways with lateral connections, novel strategies a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02136","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.02136/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":"2302.02136","created_at":"2026-07-05T05:48:05.742678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02136v2","created_at":"2026-07-05T05:48:05.742678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02136","created_at":"2026-07-05T05:48:05.742678+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4QSUGFH3V7C","created_at":"2026-07-05T05:48:05.742678+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4QSUGFH3V7CJUP5","created_at":"2026-07-05T05:48:05.742678+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4QSUGFH","created_at":"2026-07-05T05:48:05.742678+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/A4QSUGFH3V7CJUP5EUGDR3UTGF","json":"https://pith.science/pith/A4QSUGFH3V7CJUP5EUGDR3UTGF.json","graph_json":"https://pith.science/api/pith-number/A4QSUGFH3V7CJUP5EUGDR3UTGF/graph.json","events_json":"https://pith.science/api/pith-number/A4QSUGFH3V7CJUP5EUGDR3UTGF/events.json","paper":"https://pith.science/paper/A4QSUGFH"},"agent_actions":{"view_html":"https://pith.science/pith/A4QSUGFH3V7CJUP5EUGDR3UTGF","download_json":"https://pith.science/pith/A4QSUGFH3V7CJUP5EUGDR3UTGF.json","view_paper":"https://pith.science/paper/A4QSUGFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02136&json=true","fetch_graph":"https://pith.science/api/pith-number/A4QSUGFH3V7CJUP5EUGDR3UTGF/graph.json","fetch_events":"https://pith.science/api/pith-number/A4QSUGFH3V7CJUP5EUGDR3UTGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4QSUGFH3V7CJUP5EUGDR3UTGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4QSUGFH3V7CJUP5EUGDR3UTGF/action/storage_attestation","attest_author":"https://pith.science/pith/A4QSUGFH3V7CJUP5EUGDR3UTGF/action/author_attestation","sign_citation":"https://pith.science/pith/A4QSUGFH3V7CJUP5EUGDR3UTGF/action/citation_signature","submit_replication":"https://pith.science/pith/A4QSUGFH3V7CJUP5EUGDR3UTGF/action/replication_record"}},"created_at":"2026-07-05T05:48:05.742678+00:00","updated_at":"2026-07-05T05:48:05.742678+00:00"}