{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5EXARGARDHLVKVERIAPZSF3TA2","short_pith_number":"pith:5EXARGAR","schema_version":"1.0","canonical_sha256":"e92e08981119d7555491401f991773068eaf36a9f60c89eed73ca6e0dd14bc18","source":{"kind":"arxiv","id":"2402.11435","version":2},"attestation_state":"computed","paper":{"title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Fei, Juncheng Li, Long Qian, Siliang Tang, Tat-Seng Chua, Yaobo Ye, Yueting Zhuang, Yu Wu","submitted_at":"2024-02-18T03:04:38Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate remarkable proficiency in comprehending and handling text-based tasks. Many efforts are being made to transfer these attributes to video modality, which are termed Video-LLMs. However, existing Video-LLMs can only capture the coarse-grained semantics and are unable to effectively handle tasks related to comprehension or localization of specific video segments. In light of these challenges, we propose Momentor, a Video-LLM capable of accomplishing fine-grained temporal understanding tasks. To support the training of Momentor, we design an automatic data "},"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":"2402.11435","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-18T03:04:38Z","cross_cats_sorted":[],"title_canon_sha256":"c9a744224f498a1ea48872ce58a35987163689a12706826fb37070104073404a","abstract_canon_sha256":"544dfc13f02973f38f74376a9dc6cf7400ba7e0fb67335ed393fc8df269826c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:19.914982Z","signature_b64":"6vfw7gJD3WiGit7qgZ9YooQJ3fdEu8emjPzq3bzTNtwLNY4I+LJBsiw2cy9idpOlqoa2oJrGLlBaWe8gJQz6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e92e08981119d7555491401f991773068eaf36a9f60c89eed73ca6e0dd14bc18","last_reissued_at":"2026-07-05T08:26:19.914517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:19.914517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Fei, Juncheng Li, Long Qian, Siliang Tang, Tat-Seng Chua, Yaobo Ye, Yueting Zhuang, Yu Wu","submitted_at":"2024-02-18T03:04:38Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate remarkable proficiency in comprehending and handling text-based tasks. Many efforts are being made to transfer these attributes to video modality, which are termed Video-LLMs. However, existing Video-LLMs can only capture the coarse-grained semantics and are unable to effectively handle tasks related to comprehension or localization of specific video segments. In light of these challenges, we propose Momentor, a Video-LLM capable of accomplishing fine-grained temporal understanding tasks. To support the training of Momentor, we design an automatic data "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11435","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/2402.11435/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":"2402.11435","created_at":"2026-07-05T08:26:19.914577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11435v2","created_at":"2026-07-05T08:26:19.914577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11435","created_at":"2026-07-05T08:26:19.914577+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EXARGARDHLV","created_at":"2026-07-05T08:26:19.914577+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EXARGARDHLVKVER","created_at":"2026-07-05T08:26:19.914577+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EXARGAR","created_at":"2026-07-05T08:26:19.914577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25886","citing_title":"MarkIt: Training-Free Visual Markers for Precise Video Temporal Grounding","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02930","citing_title":"TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16538","citing_title":"VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06673","citing_title":"Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13803","citing_title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02860","citing_title":"A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25886","citing_title":"MarkIt: Training-Free Visual Markers for Precise Video Temporal Grounding","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08966","citing_title":"How Should Video LLMs Output Time? An Analysis of Efficient Temporal Grounding Paradigms","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08522","citing_title":"UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13106","citing_title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","ref_index":110,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5EXARGARDHLVKVERIAPZSF3TA2","json":"https://pith.science/pith/5EXARGARDHLVKVERIAPZSF3TA2.json","graph_json":"https://pith.science/api/pith-number/5EXARGARDHLVKVERIAPZSF3TA2/graph.json","events_json":"https://pith.science/api/pith-number/5EXARGARDHLVKVERIAPZSF3TA2/events.json","paper":"https://pith.science/paper/5EXARGAR"},"agent_actions":{"view_html":"https://pith.science/pith/5EXARGARDHLVKVERIAPZSF3TA2","download_json":"https://pith.science/pith/5EXARGARDHLVKVERIAPZSF3TA2.json","view_paper":"https://pith.science/paper/5EXARGAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11435&json=true","fetch_graph":"https://pith.science/api/pith-number/5EXARGARDHLVKVERIAPZSF3TA2/graph.json","fetch_events":"https://pith.science/api/pith-number/5EXARGARDHLVKVERIAPZSF3TA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EXARGARDHLVKVERIAPZSF3TA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EXARGARDHLVKVERIAPZSF3TA2/action/storage_attestation","attest_author":"https://pith.science/pith/5EXARGARDHLVKVERIAPZSF3TA2/action/author_attestation","sign_citation":"https://pith.science/pith/5EXARGARDHLVKVERIAPZSF3TA2/action/citation_signature","submit_replication":"https://pith.science/pith/5EXARGARDHLVKVERIAPZSF3TA2/action/replication_record"}},"created_at":"2026-07-05T08:26:19.914577+00:00","updated_at":"2026-07-05T08:26:19.914577+00:00"}