{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DZBM52HBBKZSQIE5SPLMMRMWDC","short_pith_number":"pith:DZBM52HB","schema_version":"1.0","canonical_sha256":"1e42cee8e10ab328209d93d6c645961897dd33b84b108bfe5d5d6b55f96cd8e2","source":{"kind":"arxiv","id":"2412.13543","version":1},"attestation_state":"computed","paper":{"title":"Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Liang Li, Li Su, Qingming Huang, Yunbin Tu","submitted_at":"2024-12-18T06:43:06Z","abstract_excerpt":"Video has emerged as a favored multimedia format on the internet. To better gain video contents, a new topic HIREST is presented, including video retrieval, moment retrieval, moment segmentation, and step-captioning. The pioneering work chooses the pre-trained CLIP-based model for video retrieval, and leverages it as a feature extractor for other three challenging tasks solved in a multi-task learning paradigm. Nevertheless, this work struggles to learn the comprehensive cognition of user-preferred content, due to disregarding the hierarchies and association relations across modalities. In thi"},"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":"2412.13543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T06:43:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8a30724bb9fd8547258fa6c6488c20ffb8c5c3df7a5ac32469e960d0312038a9","abstract_canon_sha256":"e6360c2bf01ddd506900d156de972db67bee5ae656b471216e5897b18270c29a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:03.664449Z","signature_b64":"D+44xFcnvC8cOedAqaMNXFDRCCQZRcI7/GyeJasrK23Y/JGHxxjqVCWd93yPz/i4TYBSfkQv5QykI9QJoO/NAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e42cee8e10ab328209d93d6c645961897dd33b84b108bfe5d5d6b55f96cd8e2","last_reissued_at":"2026-07-05T09:51:03.663831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:03.663831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Liang Li, Li Su, Qingming Huang, Yunbin Tu","submitted_at":"2024-12-18T06:43:06Z","abstract_excerpt":"Video has emerged as a favored multimedia format on the internet. To better gain video contents, a new topic HIREST is presented, including video retrieval, moment retrieval, moment segmentation, and step-captioning. The pioneering work chooses the pre-trained CLIP-based model for video retrieval, and leverages it as a feature extractor for other three challenging tasks solved in a multi-task learning paradigm. Nevertheless, this work struggles to learn the comprehensive cognition of user-preferred content, due to disregarding the hierarchies and association relations across modalities. In thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13543","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/2412.13543/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":"2412.13543","created_at":"2026-07-05T09:51:03.663903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13543v1","created_at":"2026-07-05T09:51:03.663903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13543","created_at":"2026-07-05T09:51:03.663903+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZBM52HBBKZS","created_at":"2026-07-05T09:51:03.663903+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZBM52HBBKZSQIE5","created_at":"2026-07-05T09:51:03.663903+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZBM52HB","created_at":"2026-07-05T09:51:03.663903+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/DZBM52HBBKZSQIE5SPLMMRMWDC","json":"https://pith.science/pith/DZBM52HBBKZSQIE5SPLMMRMWDC.json","graph_json":"https://pith.science/api/pith-number/DZBM52HBBKZSQIE5SPLMMRMWDC/graph.json","events_json":"https://pith.science/api/pith-number/DZBM52HBBKZSQIE5SPLMMRMWDC/events.json","paper":"https://pith.science/paper/DZBM52HB"},"agent_actions":{"view_html":"https://pith.science/pith/DZBM52HBBKZSQIE5SPLMMRMWDC","download_json":"https://pith.science/pith/DZBM52HBBKZSQIE5SPLMMRMWDC.json","view_paper":"https://pith.science/paper/DZBM52HB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13543&json=true","fetch_graph":"https://pith.science/api/pith-number/DZBM52HBBKZSQIE5SPLMMRMWDC/graph.json","fetch_events":"https://pith.science/api/pith-number/DZBM52HBBKZSQIE5SPLMMRMWDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZBM52HBBKZSQIE5SPLMMRMWDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZBM52HBBKZSQIE5SPLMMRMWDC/action/storage_attestation","attest_author":"https://pith.science/pith/DZBM52HBBKZSQIE5SPLMMRMWDC/action/author_attestation","sign_citation":"https://pith.science/pith/DZBM52HBBKZSQIE5SPLMMRMWDC/action/citation_signature","submit_replication":"https://pith.science/pith/DZBM52HBBKZSQIE5SPLMMRMWDC/action/replication_record"}},"created_at":"2026-07-05T09:51:03.663903+00:00","updated_at":"2026-07-05T09:51:03.663903+00:00"}