{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z2RHZNM7P7NGTLI6VAMF36FKBQ","short_pith_number":"pith:Z2RHZNM7","schema_version":"1.0","canonical_sha256":"cea27cb59f7fda69ad1ea8185df8aa0c09fe2eb88c59e63927acb4456add65e5","source":{"kind":"arxiv","id":"2312.12155","version":1},"attestation_state":"computed","paper":{"title":"Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoqing Jin, Hongtao Xie, Jiannan Ge, Jun Li, Pandeng Li, Sun-Ao Liu, Zhihang Liu","submitted_at":"2023-12-19T13:38:48Z","abstract_excerpt":"Video Moment Retrieval (VMR) aims to retrieve temporal segments in untrimmed videos corresponding to a given language query by constructing cross-modal alignment strategies. However, these existing strategies are often sub-optimal since they ignore the modality imbalance problem, \\textit{i.e.}, the semantic richness inherent in videos far exceeds that of a given limited-length sentence. Therefore, in pursuit of better alignment, a natural idea is enhancing the video modality to filter out query-irrelevant semantics, and enhancing the text modality to capture more segment-relevant knowledge. In"},"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":"2312.12155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T13:38:48Z","cross_cats_sorted":[],"title_canon_sha256":"365a320668beedd00e8f02a63799d25151d71aed4eb00523b2c398e37f00ce0f","abstract_canon_sha256":"42f935b7c124c573073b282eb2a1ef36110f136415f3dbb8fd52b76003753b70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:59.543584Z","signature_b64":"hvl83CvSdSi7rfIAPdpknJ5aaRqy19NFoi48ecZtdHqGzXK8IaSpDqLxHmSYeUw8CLq3rtQO7Sgwrljm/PFdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cea27cb59f7fda69ad1ea8185df8aa0c09fe2eb88c59e63927acb4456add65e5","last_reissued_at":"2026-07-05T07:25:59.543169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:59.543169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoqing Jin, Hongtao Xie, Jiannan Ge, Jun Li, Pandeng Li, Sun-Ao Liu, Zhihang Liu","submitted_at":"2023-12-19T13:38:48Z","abstract_excerpt":"Video Moment Retrieval (VMR) aims to retrieve temporal segments in untrimmed videos corresponding to a given language query by constructing cross-modal alignment strategies. However, these existing strategies are often sub-optimal since they ignore the modality imbalance problem, \\textit{i.e.}, the semantic richness inherent in videos far exceeds that of a given limited-length sentence. Therefore, in pursuit of better alignment, a natural idea is enhancing the video modality to filter out query-irrelevant semantics, and enhancing the text modality to capture more segment-relevant knowledge. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12155","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/2312.12155/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":"2312.12155","created_at":"2026-07-05T07:25:59.543226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12155v1","created_at":"2026-07-05T07:25:59.543226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12155","created_at":"2026-07-05T07:25:59.543226+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2RHZNM7P7NG","created_at":"2026-07-05T07:25:59.543226+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2RHZNM7P7NGTLI6","created_at":"2026-07-05T07:25:59.543226+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2RHZNM7","created_at":"2026-07-05T07:25:59.543226+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/Z2RHZNM7P7NGTLI6VAMF36FKBQ","json":"https://pith.science/pith/Z2RHZNM7P7NGTLI6VAMF36FKBQ.json","graph_json":"https://pith.science/api/pith-number/Z2RHZNM7P7NGTLI6VAMF36FKBQ/graph.json","events_json":"https://pith.science/api/pith-number/Z2RHZNM7P7NGTLI6VAMF36FKBQ/events.json","paper":"https://pith.science/paper/Z2RHZNM7"},"agent_actions":{"view_html":"https://pith.science/pith/Z2RHZNM7P7NGTLI6VAMF36FKBQ","download_json":"https://pith.science/pith/Z2RHZNM7P7NGTLI6VAMF36FKBQ.json","view_paper":"https://pith.science/paper/Z2RHZNM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12155&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2RHZNM7P7NGTLI6VAMF36FKBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2RHZNM7P7NGTLI6VAMF36FKBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2RHZNM7P7NGTLI6VAMF36FKBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2RHZNM7P7NGTLI6VAMF36FKBQ/action/storage_attestation","attest_author":"https://pith.science/pith/Z2RHZNM7P7NGTLI6VAMF36FKBQ/action/author_attestation","sign_citation":"https://pith.science/pith/Z2RHZNM7P7NGTLI6VAMF36FKBQ/action/citation_signature","submit_replication":"https://pith.science/pith/Z2RHZNM7P7NGTLI6VAMF36FKBQ/action/replication_record"}},"created_at":"2026-07-05T07:25:59.543226+00:00","updated_at":"2026-07-05T07:25:59.543226+00:00"}