{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MMGBJHTE43YRU3BPDY53R6DOYV","short_pith_number":"pith:MMGBJHTE","schema_version":"1.0","canonical_sha256":"630c149e64e6f11a6c2f1e3bb8f86ec57b25bfb7365009a4bd99a1f678d46e2f","source":{"kind":"arxiv","id":"2404.05726","version":2},"attestation_state":"computed","paper":{"title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Ashish Shah, Bo He, Hengduo Li, Menglin Jia, Ser-Nam Lim, Xuefei Cao, Young Kyun Jang","submitted_at":"2024-04-08T17:59:24Z","abstract_excerpt":"With the success of large language models (LLMs), integrating the vision model into LLMs to build vision-language foundation models has gained much more interest recently. However, existing LLM-based large multimodal models (e.g., Video-LLaMA, VideoChat) can only take in a limited number of frames for short video understanding. In this study, we mainly focus on designing an efficient and effective model for long-term video understanding. Instead of trying to process more frames simultaneously like most existing work, we propose to process videos in an online manner and store past video informa"},"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":"2404.05726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T17:59:24Z","cross_cats_sorted":[],"title_canon_sha256":"e92ab81c5284655c5a7ab73181b4842edc91310e895ce76dbe68f23fbdbe2d8a","abstract_canon_sha256":"897e88f023ddc83ea62ffeb4acc5a4537d393e3ae603bfecfe3c056b663dc163"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:43.735393Z","signature_b64":"AV88nssG8xV6FdUPTYBnvvVyJovA8kIkORhAVHo4mg8RglYvGpkSDXQZwFFrst/Bu2PQv8WgUku7VwKvferNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"630c149e64e6f11a6c2f1e3bb8f86ec57b25bfb7365009a4bd99a1f678d46e2f","last_reissued_at":"2026-07-05T08:11:43.734894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:43.734894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Ashish Shah, Bo He, Hengduo Li, Menglin Jia, Ser-Nam Lim, Xuefei Cao, Young Kyun Jang","submitted_at":"2024-04-08T17:59:24Z","abstract_excerpt":"With the success of large language models (LLMs), integrating the vision model into LLMs to build vision-language foundation models has gained much more interest recently. However, existing LLM-based large multimodal models (e.g., Video-LLaMA, VideoChat) can only take in a limited number of frames for short video understanding. In this study, we mainly focus on designing an efficient and effective model for long-term video understanding. Instead of trying to process more frames simultaneously like most existing work, we propose to process videos in an online manner and store past video informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05726","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/2404.05726/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":"2404.05726","created_at":"2026-07-05T08:11:43.734948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05726v2","created_at":"2026-07-05T08:11:43.734948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05726","created_at":"2026-07-05T08:11:43.734948+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMGBJHTE43YR","created_at":"2026-07-05T08:11:43.734948+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMGBJHTE43YRU3BP","created_at":"2026-07-05T08:11:43.734948+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMGBJHTE","created_at":"2026-07-05T08:11:43.734948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":156,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17065","citing_title":"PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning","ref_index":31,"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":46,"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":17,"is_internal_anchor":false},{"citing_arxiv_id":"2406.04264","citing_title":"MLVU: Benchmarking Multi-task Long Video Understanding","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2402.12289","citing_title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","ref_index":70,"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":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV","json":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV.json","graph_json":"https://pith.science/api/pith-number/MMGBJHTE43YRU3BPDY53R6DOYV/graph.json","events_json":"https://pith.science/api/pith-number/MMGBJHTE43YRU3BPDY53R6DOYV/events.json","paper":"https://pith.science/paper/MMGBJHTE"},"agent_actions":{"view_html":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV","download_json":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV.json","view_paper":"https://pith.science/paper/MMGBJHTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05726&json=true","fetch_graph":"https://pith.science/api/pith-number/MMGBJHTE43YRU3BPDY53R6DOYV/graph.json","fetch_events":"https://pith.science/api/pith-number/MMGBJHTE43YRU3BPDY53R6DOYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV/action/storage_attestation","attest_author":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV/action/author_attestation","sign_citation":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV/action/citation_signature","submit_replication":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV/action/replication_record"}},"created_at":"2026-07-05T08:11:43.734948+00:00","updated_at":"2026-07-05T08:11:43.734948+00:00"}