{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CYZF266RG2NMJ2LISG3F25BWAJ","short_pith_number":"pith:CYZF266R","schema_version":"1.0","canonical_sha256":"16325d7bd1369ac4e96891b65d7436026da48559e1c942d284257ba16009e70e","source":{"kind":"arxiv","id":"2312.08367","version":4},"attestation_state":"computed","paper":{"title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Kai Wang, Junbang Liang, Kenan Deng, Ming Lin, Shan Yang, Xijun Wang, Yu Lou","submitted_at":"2023-12-13T18:58:15Z","abstract_excerpt":"In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable text-guided Frame-Prompter together with a new cross-modal distillation (QFormer-Distiller) module. Pre-trained large image-language models have shown promising results on problems such as visual question answering (VQA). However, how to efficiently and effectively sample video frames when adapting pre-trained large image-language model to video-language alignmen"},"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":"2312.08367","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T18:58:15Z","cross_cats_sorted":[],"title_canon_sha256":"072b03fdd86c2c08b1329ae71fe30f8836c4f947ea4ad9914d04e4b929d30048","abstract_canon_sha256":"34824a87dea1e96487ad53c678520c2b8bd274946e6de4d0e3838d490d025c25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:48.759069Z","signature_b64":"210ocigA/sVhzYTNV3vohFbngbpsbJVeMM8gA0QdWj8N6Jm6Zp6q/U/gljRgQ9H5Nltnajz8DtI9lJSz+nFKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16325d7bd1369ac4e96891b65d7436026da48559e1c942d284257ba16009e70e","last_reissued_at":"2026-07-05T09:13:48.758618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:48.758618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Kai Wang, Junbang Liang, Kenan Deng, Ming Lin, Shan Yang, Xijun Wang, Yu Lou","submitted_at":"2023-12-13T18:58:15Z","abstract_excerpt":"In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable text-guided Frame-Prompter together with a new cross-modal distillation (QFormer-Distiller) module. Pre-trained large image-language models have shown promising results on problems such as visual question answering (VQA). However, how to efficiently and effectively sample video frames when adapting pre-trained large image-language model to video-language alignmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08367","kind":"arxiv","version":4},"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/2312.08367/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":"2312.08367","created_at":"2026-07-05T09:13:48.758671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08367v4","created_at":"2026-07-05T09:13:48.758671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08367","created_at":"2026-07-05T09:13:48.758671+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYZF266RG2NM","created_at":"2026-07-05T09:13:48.758671+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYZF266RG2NMJ2LI","created_at":"2026-07-05T09:13:48.758671+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYZF266R","created_at":"2026-07-05T09:13:48.758671+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29445","citing_title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CYZF266RG2NMJ2LISG3F25BWAJ","json":"https://pith.science/pith/CYZF266RG2NMJ2LISG3F25BWAJ.json","graph_json":"https://pith.science/api/pith-number/CYZF266RG2NMJ2LISG3F25BWAJ/graph.json","events_json":"https://pith.science/api/pith-number/CYZF266RG2NMJ2LISG3F25BWAJ/events.json","paper":"https://pith.science/paper/CYZF266R"},"agent_actions":{"view_html":"https://pith.science/pith/CYZF266RG2NMJ2LISG3F25BWAJ","download_json":"https://pith.science/pith/CYZF266RG2NMJ2LISG3F25BWAJ.json","view_paper":"https://pith.science/paper/CYZF266R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08367&json=true","fetch_graph":"https://pith.science/api/pith-number/CYZF266RG2NMJ2LISG3F25BWAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CYZF266RG2NMJ2LISG3F25BWAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYZF266RG2NMJ2LISG3F25BWAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYZF266RG2NMJ2LISG3F25BWAJ/action/storage_attestation","attest_author":"https://pith.science/pith/CYZF266RG2NMJ2LISG3F25BWAJ/action/author_attestation","sign_citation":"https://pith.science/pith/CYZF266RG2NMJ2LISG3F25BWAJ/action/citation_signature","submit_replication":"https://pith.science/pith/CYZF266RG2NMJ2LISG3F25BWAJ/action/replication_record"}},"created_at":"2026-07-05T09:13:48.758671+00:00","updated_at":"2026-07-05T09:13:48.758671+00:00"}