{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5JQVIKBXEADQUVDI6MWPMANDTR","short_pith_number":"pith:5JQVIKBX","schema_version":"1.0","canonical_sha256":"ea6154283720070a5468f32cf601a39c72867b05e3e86eb91b6333d3b1babc03","source":{"kind":"arxiv","id":"2407.15047","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chang Liu, Dongyan Zhao, Jianxin Liang, Qun Liu, Xiaojun Meng, Yueqian Wang","submitted_at":"2024-07-21T04:09:37Z","abstract_excerpt":"Video Question Answering (VideoQA) has emerged as a challenging frontier in the field of multimedia processing, requiring intricate interactions between visual and textual modalities. Simply uniformly sampling frames or indiscriminately aggregating frame-level visual features often falls short in capturing the nuanced and relevant contexts of videos to well perform VideoQA. To mitigate these issues, we propose VidF4, a novel VideoQA framework equipped with tailored frame selection strategy for effective and efficient VideoQA. We propose three frame-scoring mechanisms that consider both questio"},"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":"2407.15047","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T04:09:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"723fc753be110e95a7e645c253b56e97c77ba1c7d2d7bc37e0e11fbbd647385d","abstract_canon_sha256":"d8f65157215d57923e2b41616f0229f07aa899227618d24a3d31cc6881ef3c2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:22.912598Z","signature_b64":"/0YJ6AOGAYpcsnS6BH7BrZLxhurKjxd0FaPFETut0b8wUSIzop0VAVdIXxirnL+MB0e2LMEevGp9VAdKSK4fCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea6154283720070a5468f32cf601a39c72867b05e3e86eb91b6333d3b1babc03","last_reissued_at":"2026-07-05T08:47:22.912061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:22.912061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chang Liu, Dongyan Zhao, Jianxin Liang, Qun Liu, Xiaojun Meng, Yueqian Wang","submitted_at":"2024-07-21T04:09:37Z","abstract_excerpt":"Video Question Answering (VideoQA) has emerged as a challenging frontier in the field of multimedia processing, requiring intricate interactions between visual and textual modalities. Simply uniformly sampling frames or indiscriminately aggregating frame-level visual features often falls short in capturing the nuanced and relevant contexts of videos to well perform VideoQA. To mitigate these issues, we propose VidF4, a novel VideoQA framework equipped with tailored frame selection strategy for effective and efficient VideoQA. We propose three frame-scoring mechanisms that consider both questio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15047","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/2407.15047/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":"2407.15047","created_at":"2026-07-05T08:47:22.912122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15047v2","created_at":"2026-07-05T08:47:22.912122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15047","created_at":"2026-07-05T08:47:22.912122+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JQVIKBXEADQ","created_at":"2026-07-05T08:47:22.912122+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JQVIKBXEADQUVDI","created_at":"2026-07-05T08:47:22.912122+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JQVIKBX","created_at":"2026-07-05T08:47:22.912122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19075","citing_title":"CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08410","citing_title":"Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22911","citing_title":"ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00444","citing_title":"Scaling Video Understanding via Compact Latent Multi-Agent Collaboration","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5JQVIKBXEADQUVDI6MWPMANDTR","json":"https://pith.science/pith/5JQVIKBXEADQUVDI6MWPMANDTR.json","graph_json":"https://pith.science/api/pith-number/5JQVIKBXEADQUVDI6MWPMANDTR/graph.json","events_json":"https://pith.science/api/pith-number/5JQVIKBXEADQUVDI6MWPMANDTR/events.json","paper":"https://pith.science/paper/5JQVIKBX"},"agent_actions":{"view_html":"https://pith.science/pith/5JQVIKBXEADQUVDI6MWPMANDTR","download_json":"https://pith.science/pith/5JQVIKBXEADQUVDI6MWPMANDTR.json","view_paper":"https://pith.science/paper/5JQVIKBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15047&json=true","fetch_graph":"https://pith.science/api/pith-number/5JQVIKBXEADQUVDI6MWPMANDTR/graph.json","fetch_events":"https://pith.science/api/pith-number/5JQVIKBXEADQUVDI6MWPMANDTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JQVIKBXEADQUVDI6MWPMANDTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JQVIKBXEADQUVDI6MWPMANDTR/action/storage_attestation","attest_author":"https://pith.science/pith/5JQVIKBXEADQUVDI6MWPMANDTR/action/author_attestation","sign_citation":"https://pith.science/pith/5JQVIKBXEADQUVDI6MWPMANDTR/action/citation_signature","submit_replication":"https://pith.science/pith/5JQVIKBXEADQUVDI6MWPMANDTR/action/replication_record"}},"created_at":"2026-07-05T08:47:22.912122+00:00","updated_at":"2026-07-05T08:47:22.912122+00:00"}