{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YFLLQD47JIVUI73MKA3J2PCSRJ","short_pith_number":"pith:YFLLQD47","schema_version":"1.0","canonical_sha256":"c156b80f9f4a2b447f6c50369d3c528a6266760b1b6da358c153a021954f1b82","source":{"kind":"arxiv","id":"2503.09149","version":2},"attestation_state":"computed","paper":{"title":"Memory-enhanced Retrieval Augmentation for Long Video Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Hongjin Qian, Huaying Yuan, Ji-Rong Wen, Minghao Qin, Nicu Sebe, Yan Shu, Zheng Liu, Zhicheng Dou","submitted_at":"2025-03-12T08:23:32Z","abstract_excerpt":"Efficient long-video understanding~(LVU) remains a challenging task in computer vision. Current long-context vision-language models~(LVLMs) suffer from information loss due to compression and brute-force downsampling. While retrieval-augmented generation (RAG) methods mitigate this issue, their applicability is limited due to explicit query dependency. To overcome this challenge, we introduce a novel memory-enhanced RAG-based approach called MemVid, which is inspired by the cognitive memory of human beings. Our approach operates in four basic steps: 1) memorizing holistic video information, 2)"},"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":"2503.09149","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T08:23:32Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"2d7d1d728d01bce8b3f552440ddc06fae8a43d083b99f7f19dd615cb06861cc3","abstract_canon_sha256":"bbe9f81ddf0fac473c6c0c27094ebd4c14d4a28c576a6e69c4869cdf90f33a34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:16.294957Z","signature_b64":"oDSAVKBhkb9pB1q/YaoQZhqi8tLT0kIbnvT/VfS+DUcDpX/XKLuxWs9mqLGudqfq0CzMg8VEXEQniCoScAZhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c156b80f9f4a2b447f6c50369d3c528a6266760b1b6da358c153a021954f1b82","last_reissued_at":"2026-07-05T11:24:16.294436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:16.294436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory-enhanced Retrieval Augmentation for Long Video Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Hongjin Qian, Huaying Yuan, Ji-Rong Wen, Minghao Qin, Nicu Sebe, Yan Shu, Zheng Liu, Zhicheng Dou","submitted_at":"2025-03-12T08:23:32Z","abstract_excerpt":"Efficient long-video understanding~(LVU) remains a challenging task in computer vision. Current long-context vision-language models~(LVLMs) suffer from information loss due to compression and brute-force downsampling. While retrieval-augmented generation (RAG) methods mitigate this issue, their applicability is limited due to explicit query dependency. To overcome this challenge, we introduce a novel memory-enhanced RAG-based approach called MemVid, which is inspired by the cognitive memory of human beings. Our approach operates in four basic steps: 1) memorizing holistic video information, 2)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09149","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/2503.09149/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":"2503.09149","created_at":"2026-07-05T11:24:16.294507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09149v2","created_at":"2026-07-05T11:24:16.294507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09149","created_at":"2026-07-05T11:24:16.294507+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFLLQD47JIVU","created_at":"2026-07-05T11:24:16.294507+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFLLQD47JIVUI73M","created_at":"2026-07-05T11:24:16.294507+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFLLQD47","created_at":"2026-07-05T11:24:16.294507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00825","citing_title":"SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20913","citing_title":"LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00814","citing_title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00814","citing_title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YFLLQD47JIVUI73MKA3J2PCSRJ","json":"https://pith.science/pith/YFLLQD47JIVUI73MKA3J2PCSRJ.json","graph_json":"https://pith.science/api/pith-number/YFLLQD47JIVUI73MKA3J2PCSRJ/graph.json","events_json":"https://pith.science/api/pith-number/YFLLQD47JIVUI73MKA3J2PCSRJ/events.json","paper":"https://pith.science/paper/YFLLQD47"},"agent_actions":{"view_html":"https://pith.science/pith/YFLLQD47JIVUI73MKA3J2PCSRJ","download_json":"https://pith.science/pith/YFLLQD47JIVUI73MKA3J2PCSRJ.json","view_paper":"https://pith.science/paper/YFLLQD47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09149&json=true","fetch_graph":"https://pith.science/api/pith-number/YFLLQD47JIVUI73MKA3J2PCSRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YFLLQD47JIVUI73MKA3J2PCSRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFLLQD47JIVUI73MKA3J2PCSRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFLLQD47JIVUI73MKA3J2PCSRJ/action/storage_attestation","attest_author":"https://pith.science/pith/YFLLQD47JIVUI73MKA3J2PCSRJ/action/author_attestation","sign_citation":"https://pith.science/pith/YFLLQD47JIVUI73MKA3J2PCSRJ/action/citation_signature","submit_replication":"https://pith.science/pith/YFLLQD47JIVUI73MKA3J2PCSRJ/action/replication_record"}},"created_at":"2026-07-05T11:24:16.294507+00:00","updated_at":"2026-07-05T11:24:16.294507+00:00"}