{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZUT2E4YMUTYS74WQHIIZMK42KW","short_pith_number":"pith:ZUT2E4YM","schema_version":"1.0","canonical_sha256":"cd27a2730ca4f12ff2d03a11962b9a55ac93dbf1d290ad863018cf74457004df","source":{"kind":"arxiv","id":"2307.16449","version":4},"attestation_state":"computed","paper":{"title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enxin Song, Feiyang Wu, Gaoang Wang, Guanhong Wang, Haoyang Zhou, Haozhe Chi, Jenq-Neng Hwang, Tian Ye, Wenhao Chai, Xun Guo, Yan Lu, Yanting Zhang, Yucheng Zhang","submitted_at":"2023-07-31T07:15:45Z","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 systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose additional challenges. Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose the MovieChat to overcome these chall"},"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":"2307.16449","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T07:15:45Z","cross_cats_sorted":[],"title_canon_sha256":"e84af2c403037f9d168ab2f11dd416251a1a8991e8ba734c551c2862e7d8dc6f","abstract_canon_sha256":"3ce611187385e10e9e24e593985acb313eafd2824384d28ccf4028c5e921714c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:02.490593Z","signature_b64":"J7qXrbJXdq2BE8XVIgS2DkV1q6OPZ728wNPEs0zESb8EUkK32GDqQqaJdLvDYHYSx0v0JErnSpCeWa6aJFzFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd27a2730ca4f12ff2d03a11962b9a55ac93dbf1d290ad863018cf74457004df","last_reissued_at":"2026-07-05T07:54:02.490081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:02.490081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enxin Song, Feiyang Wu, Gaoang Wang, Guanhong Wang, Haoyang Zhou, Haozhe Chi, Jenq-Neng Hwang, Tian Ye, Wenhao Chai, Xun Guo, Yan Lu, Yanting Zhang, Yucheng Zhang","submitted_at":"2023-07-31T07:15:45Z","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 systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose additional challenges. Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose the MovieChat to overcome these chall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16449","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/2307.16449/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":"2307.16449","created_at":"2026-07-05T07:54:02.490141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16449v4","created_at":"2026-07-05T07:54:02.490141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16449","created_at":"2026-07-05T07:54:02.490141+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUT2E4YMUTYS","created_at":"2026-07-05T07:54:02.490141+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUT2E4YMUTYS74WQ","created_at":"2026-07-05T07:54:02.490141+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUT2E4YM","created_at":"2026-07-05T07:54:02.490141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08032","citing_title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","ref_index":108,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05736","citing_title":"VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29445","citing_title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05067","citing_title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17065","citing_title":"PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2406.08035","citing_title":"LVBench: An Extreme Long Video Understanding Benchmark","ref_index":34,"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":135,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16994","citing_title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27259","citing_title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2406.04264","citing_title":"MLVU: Benchmarking Multi-task Long Video Understanding","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13826","citing_title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2504.05299","citing_title":"SmolVLM: Redefining small and efficient multimodal models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2406.07476","citing_title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUT2E4YMUTYS74WQHIIZMK42KW","json":"https://pith.science/pith/ZUT2E4YMUTYS74WQHIIZMK42KW.json","graph_json":"https://pith.science/api/pith-number/ZUT2E4YMUTYS74WQHIIZMK42KW/graph.json","events_json":"https://pith.science/api/pith-number/ZUT2E4YMUTYS74WQHIIZMK42KW/events.json","paper":"https://pith.science/paper/ZUT2E4YM"},"agent_actions":{"view_html":"https://pith.science/pith/ZUT2E4YMUTYS74WQHIIZMK42KW","download_json":"https://pith.science/pith/ZUT2E4YMUTYS74WQHIIZMK42KW.json","view_paper":"https://pith.science/paper/ZUT2E4YM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16449&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUT2E4YMUTYS74WQHIIZMK42KW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUT2E4YMUTYS74WQHIIZMK42KW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUT2E4YMUTYS74WQHIIZMK42KW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUT2E4YMUTYS74WQHIIZMK42KW/action/storage_attestation","attest_author":"https://pith.science/pith/ZUT2E4YMUTYS74WQHIIZMK42KW/action/author_attestation","sign_citation":"https://pith.science/pith/ZUT2E4YMUTYS74WQHIIZMK42KW/action/citation_signature","submit_replication":"https://pith.science/pith/ZUT2E4YMUTYS74WQHIIZMK42KW/action/replication_record"}},"created_at":"2026-07-05T07:54:02.490141+00:00","updated_at":"2026-07-05T07:54:02.490141+00:00"}