{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KHUIB7STW3WDHE4D7XYHESBIXA","short_pith_number":"pith:KHUIB7ST","schema_version":"1.0","canonical_sha256":"51e880fe53b6ec339383fdf0724828b815306c93b56c660e00a57e0f4c45acd4","source":{"kind":"arxiv","id":"2404.17176","version":1},"attestation_state":"computed","paper":{"title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enxin Song, Gaoang Wang, Jenq-Neng Hwang, Tian Ye, Wenhao Chai, Xi Li","submitted_at":"2024-04-26T06:17:04Z","abstract_excerpt":"Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing methods either employ complex spatial-temporal modules or rely heavily on additional perception models to extract temporal features for video understanding, and they only perform well on short videos. For long videos, the computational complexity and memory costs associated with long-term temporal connections are significantly increased, posing additional challenges.Taking advantage of the Atkinson-Shiffri"},"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":"2404.17176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T06:17:04Z","cross_cats_sorted":[],"title_canon_sha256":"dad6ee1189a484b7a74bfd235050aaebda475bd790da777a0822338ecce49347","abstract_canon_sha256":"c3d84e86618499d919d221601c38fc37bbe4c57805ce870ac712b75fcae64346"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:34.007640Z","signature_b64":"hYZ58rlpZDtgOE1GeNmzUJ2vgecPLxMMAdg9cMuA8kMEU9oB8C73Y058PKNAFB8+zmcZ9/8gt9cNWl4UxLRiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51e880fe53b6ec339383fdf0724828b815306c93b56c660e00a57e0f4c45acd4","last_reissued_at":"2026-07-05T08:12:34.007131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:34.007131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enxin Song, Gaoang Wang, Jenq-Neng Hwang, Tian Ye, Wenhao Chai, Xi Li","submitted_at":"2024-04-26T06:17:04Z","abstract_excerpt":"Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing methods either employ complex spatial-temporal modules or rely heavily on additional perception models to extract temporal features for video understanding, and they only perform well on short videos. For long videos, the computational complexity and memory costs associated with long-term temporal connections are significantly increased, posing additional challenges.Taking advantage of the Atkinson-Shiffri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17176","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/2404.17176/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":"2404.17176","created_at":"2026-07-05T08:12:34.007192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17176v1","created_at":"2026-07-05T08:12:34.007192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17176","created_at":"2026-07-05T08:12:34.007192+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHUIB7STW3WD","created_at":"2026-07-05T08:12:34.007192+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHUIB7STW3WDHE4D","created_at":"2026-07-05T08:12:34.007192+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHUIB7ST","created_at":"2026-07-05T08:12:34.007192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17798","citing_title":"LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06991","citing_title":"Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2412.17574","citing_title":"HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15269","citing_title":"LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13106","citing_title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA","json":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA.json","graph_json":"https://pith.science/api/pith-number/KHUIB7STW3WDHE4D7XYHESBIXA/graph.json","events_json":"https://pith.science/api/pith-number/KHUIB7STW3WDHE4D7XYHESBIXA/events.json","paper":"https://pith.science/paper/KHUIB7ST"},"agent_actions":{"view_html":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA","download_json":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA.json","view_paper":"https://pith.science/paper/KHUIB7ST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17176&json=true","fetch_graph":"https://pith.science/api/pith-number/KHUIB7STW3WDHE4D7XYHESBIXA/graph.json","fetch_events":"https://pith.science/api/pith-number/KHUIB7STW3WDHE4D7XYHESBIXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA/action/storage_attestation","attest_author":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA/action/author_attestation","sign_citation":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA/action/citation_signature","submit_replication":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA/action/replication_record"}},"created_at":"2026-07-05T08:12:34.007192+00:00","updated_at":"2026-07-05T08:12:34.007192+00:00"}