{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:37NJHHNI7A3GSOVGZGIFLL4ATW","short_pith_number":"pith:37NJHHNI","schema_version":"1.0","canonical_sha256":"dfda939da8f836693aa6c99055af809d9719fde8767a4612ff0dadacb0de4d12","source":{"kind":"arxiv","id":"2405.12540","version":1},"attestation_state":"computed","paper":{"title":"Context-Enhanced Video Moment Retrieval with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Ajmal Mian, Bo Liu, Bo Miao, Jiuxin Cao, Mehwish Nasim, Weijia Liu, Xuelin Zhu","submitted_at":"2024-05-21T07:12:27Z","abstract_excerpt":"Current methods for Video Moment Retrieval (VMR) struggle to align complex situations involving specific environmental details, character descriptions, and action narratives. To tackle this issue, we propose a Large Language Model-guided Moment Retrieval (LMR) approach that employs the extensive knowledge of Large Language Models (LLMs) to improve video context representation as well as cross-modal alignment, facilitating accurate localization of target moments. Specifically, LMR introduces a context enhancement technique with LLMs to generate crucial target-related context semantics. These se"},"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":"2405.12540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T07:12:27Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"7eb44fd17a2c2c9b38afd90c70d76bfbcd30a8df986b1d5ce8147fba25e0c87a","abstract_canon_sha256":"a9b7dcefe606c8ef107284fc461f5dac8e876f1ca277b6f187b54f429d90871f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:21.596392Z","signature_b64":"TQ8ayuQTy2r8DCa0zyCvRXSA8pvXfDRytkf7gFq3ESduTTWvceh5MjdzDaLf3JPz5gGz4h19jhjOlpzvXyqvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfda939da8f836693aa6c99055af809d9719fde8767a4612ff0dadacb0de4d12","last_reissued_at":"2026-07-05T08:21:21.595877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:21.595877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Enhanced Video Moment Retrieval with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Ajmal Mian, Bo Liu, Bo Miao, Jiuxin Cao, Mehwish Nasim, Weijia Liu, Xuelin Zhu","submitted_at":"2024-05-21T07:12:27Z","abstract_excerpt":"Current methods for Video Moment Retrieval (VMR) struggle to align complex situations involving specific environmental details, character descriptions, and action narratives. To tackle this issue, we propose a Large Language Model-guided Moment Retrieval (LMR) approach that employs the extensive knowledge of Large Language Models (LLMs) to improve video context representation as well as cross-modal alignment, facilitating accurate localization of target moments. Specifically, LMR introduces a context enhancement technique with LLMs to generate crucial target-related context semantics. These se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12540","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/2405.12540/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":"2405.12540","created_at":"2026-07-05T08:21:21.595943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12540v1","created_at":"2026-07-05T08:21:21.595943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12540","created_at":"2026-07-05T08:21:21.595943+00:00"},{"alias_kind":"pith_short_12","alias_value":"37NJHHNI7A3G","created_at":"2026-07-05T08:21:21.595943+00:00"},{"alias_kind":"pith_short_16","alias_value":"37NJHHNI7A3GSOVG","created_at":"2026-07-05T08:21:21.595943+00:00"},{"alias_kind":"pith_short_8","alias_value":"37NJHHNI","created_at":"2026-07-05T08:21:21.595943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37NJHHNI7A3GSOVGZGIFLL4ATW","json":"https://pith.science/pith/37NJHHNI7A3GSOVGZGIFLL4ATW.json","graph_json":"https://pith.science/api/pith-number/37NJHHNI7A3GSOVGZGIFLL4ATW/graph.json","events_json":"https://pith.science/api/pith-number/37NJHHNI7A3GSOVGZGIFLL4ATW/events.json","paper":"https://pith.science/paper/37NJHHNI"},"agent_actions":{"view_html":"https://pith.science/pith/37NJHHNI7A3GSOVGZGIFLL4ATW","download_json":"https://pith.science/pith/37NJHHNI7A3GSOVGZGIFLL4ATW.json","view_paper":"https://pith.science/paper/37NJHHNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12540&json=true","fetch_graph":"https://pith.science/api/pith-number/37NJHHNI7A3GSOVGZGIFLL4ATW/graph.json","fetch_events":"https://pith.science/api/pith-number/37NJHHNI7A3GSOVGZGIFLL4ATW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37NJHHNI7A3GSOVGZGIFLL4ATW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37NJHHNI7A3GSOVGZGIFLL4ATW/action/storage_attestation","attest_author":"https://pith.science/pith/37NJHHNI7A3GSOVGZGIFLL4ATW/action/author_attestation","sign_citation":"https://pith.science/pith/37NJHHNI7A3GSOVGZGIFLL4ATW/action/citation_signature","submit_replication":"https://pith.science/pith/37NJHHNI7A3GSOVGZGIFLL4ATW/action/replication_record"}},"created_at":"2026-07-05T08:21:21.595943+00:00","updated_at":"2026-07-05T08:21:21.595943+00:00"}